{
  "evidence_cutoff": "2026-08-09",
  "status_vocabulary": ["peer-reviewed", "preprint", "industry-report", "benchmark-program"],
  "sources": [
    {"id":"sparck-jones-1972","first_public":"1972","title":"A Statistical Interpretation of Term Specificity and Its Application in Retrieval","venue":"Journal of Documentation","status":"peer-reviewed","primary_url":"https://doi.org/10.1108/eb026526","topics":["tf-idf","sparse-retrieval"]},
    {"id":"salton-vector-space-1975","first_public":"1975","title":"A Vector Space Model for Automatic Indexing","venue":"Communications of the ACM","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/361219.361220","topics":["vector-space","information-retrieval"]},
    {"id":"rsj-1976","first_public":"1976","title":"Relevance Weighting of Search Terms","venue":"JASIS","status":"peer-reviewed","primary_url":"https://doi.org/10.1002/asi.4630270302","topics":["probabilistic-ir","term-weighting"]},
    {"id":"bm25-trec3","first_public":"1994-11","title":"Okapi at TREC-3","venue":"TREC-3 / NIST SP 500-225","status":"peer-reviewed","primary_url":"https://pages.nist.gov/trec-browser/trec3/proceedings/","topics":["bm25","sparse-retrieval"]},
    {"id":"memory-networks","first_public":"2014-10-15","title":"Memory Networks","venue":"ICLR 2015","status":"peer-reviewed","primary_url":"https://arxiv.org/abs/1410.3916","topics":["memory","multi-hop"]},
    {"id":"memn2n","first_public":"2015-03-31","title":"End-To-End Memory Networks","venue":"NeurIPS 2015","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper/2015/hash/8fb21ee7a2207526da55a679f0332de2-Abstract.html","topics":["memory","differentiable-retrieval"]},
    {"id":"drqa","first_public":"2017-03-31","title":"Reading Wikipedia to Answer Open-Domain Questions","venue":"ACL 2017","status":"peer-reviewed","primary_url":"https://aclanthology.org/P17-1171/","topics":["open-qa","tf-idf","reader"]},
    {"id":"retrieve-refine","first_public":"2018","title":"Retrieve and Refine: Improved Sequence Generation Models for Dialogue","venue":"EMNLP SCAI 2018","status":"peer-reviewed","primary_url":"https://aclanthology.org/W18-5713/","topics":["generation","dialogue"]},
    {"id":"wizard-wikipedia","first_public":"2018","title":"Wizard of Wikipedia: Knowledge-Powered Conversational Agents","venue":"ICLR 2019","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=r1l73iRqKm","topics":["dialogue","knowledge-grounding"]},
    {"id":"orqa","first_public":"2019-06-01","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","venue":"ACL 2019","status":"peer-reviewed","primary_url":"https://aclanthology.org/P19-1612/","topics":["dense-retrieval","latent-evidence","ict"]},
    {"id":"knn-lm","first_public":"2019-11-01","title":"Generalization through Memorization: Nearest Neighbor Language Models","venue":"ICLR 2020","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=HklBjCEKvH","topics":["language-modeling","non-parametric-memory"]},
    {"id":"realm","first_public":"2020-02-10","title":"REALM: Retrieval-Augmented Language Model Pre-Training","venue":"ICML 2020","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v119/guu20a.html","topics":["pretraining","latent-retrieval","index-refresh"]},
    {"id":"dpr","first_public":"2020-04-10","title":"Dense Passage Retrieval for Open-Domain Question Answering","venue":"EMNLP 2020","status":"peer-reviewed","primary_url":"https://aclanthology.org/2020.emnlp-main.550/","topics":["dense-retrieval","contrastive-learning","faiss"]},
    {"id":"rag","first_public":"2020-05-22","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","venue":"NeurIPS 2020","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html","topics":["rag","latent-documents","seq2seq"]},
    {"id":"marge","first_public":"2020-06-26","title":"Pre-training via Paraphrasing","venue":"NeurIPS 2020","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper/2020/hash/d6f1dd034aabde7657e6680444ceff62-Abstract.html","topics":["pretraining","multilingual","retrieval"]},
    {"id":"fid","first_public":"2020-07-02","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","venue":"EACL 2021","status":"peer-reviewed","primary_url":"https://aclanthology.org/2021.eacl-main.74/","topics":["fusion-in-decoder","multi-passage"]},
    {"id":"fid-kd","first_public":"2020-12-08","title":"Distilling Knowledge from Reader to Retriever for Question Answering","venue":"ICLR 2021","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=NTEz-6wysdb","topics":["distillation","reader-to-retriever"]},
    {"id":"spalm","first_public":"2020","title":"Adaptive Semiparametric Language Models","venue":"TACL 2021","status":"peer-reviewed","primary_url":"https://aclanthology.org/2021.tacl-1.22/","topics":["memory","adaptive-fusion"]},
    {"id":"kilt","first_public":"2020","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","venue":"NAACL 2021","status":"peer-reviewed","primary_url":"https://aclanthology.org/2021.naacl-main.200/","topics":["benchmark","provenance","wikipedia"]},
    {"id":"emdr2","first_public":"2021-06-09","title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","venue":"NeurIPS 2021","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper/2021/hash/da3fde159d754a2555eaa198d2d105b2-Abstract.html","topics":["joint-training","multi-document"]},
    {"id":"spladev2","first_public":"2021-09","title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2109.10086","topics":["learned-sparse","expansion"]},
    {"id":"retro","first_public":"2021-12-08","title":"Improving Language Models by Retrieving from Trillions of Tokens","venue":"ICML 2022","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v162/borgeaud22a.html","topics":["pretraining","chunk-retrieval","scaling"]},
    {"id":"contriever","first_public":"2021-12-16","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","venue":"TMLR 2022","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=jKN1pXi7b0","topics":["dense-retrieval","unsupervised"]},
    {"id":"colbertv2","first_public":"2021-12-03","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","venue":"NAACL 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.naacl-main.272/","topics":["late-interaction","compression"]},
    {"id":"atlas","first_public":"2022-08-05","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","venue":"JMLR 2023","status":"peer-reviewed","primary_url":"https://jmlr.org/papers/v24/23-0037.html","topics":["pretraining","few-shot","distillation"]},
    {"id":"react","first_public":"2022-10-06","title":"ReAct: Synergizing Reasoning and Acting in Language Models","venue":"ICLR 2023","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=WE_vluYUL-X","topics":["agents","tool-use","reasoning"]},
    {"id":"murag","first_public":"2022-10-06","title":"MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text","venue":"EMNLP 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.emnlp-main.375/","topics":["multimodal","images","qa"]},
    {"id":"ra-cm3","first_public":"2022-11-22","title":"Retrieval-Augmented Multimodal Language Modeling","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2211.12561","topics":["multimodal","generation"]},
    {"id":"hyde","first_public":"2022-12-20","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","venue":"ACL 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.acl-long.99/","topics":["query-transformation","hypothetical-document"]},
    {"id":"query2doc","first_public":"2023-03-14","title":"Query2doc: Query Expansion with Large Language Models","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2303.07678","topics":["query-expansion","pseudo-document"]},
    {"id":"flare","first_public":"2023-05-11","title":"Active Retrieval Augmented Generation","venue":"EMNLP 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.emnlp-main.495/","topics":["active-retrieval","uncertainty"]},
    {"id":"rewrite-retrieve-read","first_public":"2023-05-23","title":"Query Rewriting for Retrieval-Augmented Large Language Models","venue":"EMNLP 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.emnlp-main.322/","topics":["query-rewriting","reinforcement-learning"]},
    {"id":"iter-retgen","first_public":"2023-05-24","title":"Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2305.15294","topics":["iterative-retrieval","generation"]},
    {"id":"lost-middle","first_public":"2023-07-06","title":"Lost in the Middle: How Language Models Use Long Contexts","venue":"TACL 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.tacl-1.9/","topics":["long-context","position","distraction"]},
    {"id":"self-rag","first_public":"2023-10-17","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","venue":"ICLR 2024","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=hSyW5go0v8","topics":["adaptive-retrieval","reflection","citations"]},
    {"id":"corrective-rag","first_public":"2024-01-29","title":"Corrective Retrieval Augmented Generation","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2401.15884","topics":["correction","web-search","routing"]},
    {"id":"raptor","first_public":"2024-01-31","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","venue":"ICLR 2024","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=GN921JHCRw","topics":["hierarchical-retrieval","summaries"]},
    {"id":"adaptive-rag","first_public":"2024-03-21","title":"Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity","venue":"NAACL 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.naacl-long.389/","topics":["routing","complexity","efficiency"]},
    {"id":"graphrag","first_public":"2024-04-24","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","venue":"Microsoft Research","status":"industry-report","primary_url":"https://www.microsoft.com/en-us/research/publication/from-local-to-global-a-graph-rag-approach-to-query-focused-summarization/","topics":["graph","global-synthesis","communities"]},
    {"id":"hipporag","first_public":"2024","title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","venue":"NeurIPS 2024","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2024/hash/6ddc81d76dc3e20c1cdbda4a040d11ae-Abstract-Conference.html","topics":["graph","pagerank","multi-hop"]},
    {"id":"rankrag","first_public":"2024","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","venue":"NeurIPS 2024","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2024/hash/db93ccb7cb70e655c1af7d7a2433e6ae-Abstract-Conference.html","topics":["reranking","instruction-tuning"]},
    {"id":"rag-vs-long-context","first_public":"2024-07-23","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","venue":"EMNLP Industry 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.emnlp-industry.66/","topics":["long-context","routing","self-route"]},
    {"id":"colpali","first_public":"2024-06-27","title":"ColPali: Efficient Document Retrieval with Vision Language Models","venue":"ICLR 2025","status":"peer-reviewed","primary_url":"https://proceedings.iclr.cc/paper_files/paper/2025/hash/99e9cf99cc114c46c2e6168e4dc0c43a-Abstract-Conference.html","topics":["visual-retrieval","late-interaction","documents"]},
    {"id":"ralmspec","first_public":"2024","title":"RaLMSpec: Accelerating Retrieval-Augmented Language Model Serving with Speculation","venue":"ICML 2024","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v235/zhang24cq.html","topics":["systems","latency","speculation"]},
    {"id":"search-r1","first_public":"2025","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","venue":"COLM 2025","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=Rwhi91ideu","topics":["agentic-rag","reinforcement-learning","search"]},
    {"id":"research-agent","first_public":"2025","title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","venue":"NeurIPS 2025","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=OuGAwwAT8G","topics":["agentic-rag","grpo"]},
    {"id":"stepsearch","first_public":"2025","title":"StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization","venue":"EMNLP 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.emnlp-main.1106/","topics":["agentic-rag","process-reward"]},
    {"id":"reasonir","first_public":"2025","title":"ReasonIR: Training Retrievers for Reasoning Tasks","venue":"COLM 2025","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=kkBCNLMbGj","topics":["reasoning-retrieval","hard-negatives"]},
    {"id":"gritlm","first_public":"2024","title":"Generative Representational Instruction Tuning","venue":"ICLR 2025","status":"peer-reviewed","primary_url":"https://proceedings.iclr.cc/paper_files/paper/2025/hash/70cfb8e8c9e142e87e33f329be4ddf86-Abstract-Conference.html","topics":["embeddings","generation","efficiency"]},
    {"id":"hipporag2","first_public":"2025","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","venue":"ICML 2025","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v267/gutierrez25a.html","topics":["graph","memory","multi-hop"]},
    {"id":"long-context-meets-rag","first_public":"2024","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","venue":"ICLR 2025","status":"peer-reviewed","primary_url":"https://proceedings.iclr.cc/paper_files/paper/2025/hash/5df56b0238e56b953d4600d1b9e83982-Abstract-Conference.html","topics":["long-context","distraction","top-k"]},
    {"id":"sufficient-context","first_public":"2024","title":"Sufficient Context: A New Lens on Retrieval Augmented Generation Systems","venue":"ICLR 2025","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=8N8hWwTj6D","topics":["abstention","context-sufficiency"]},
    {"id":"think-cite","first_public":"2025","title":"Think&Cite: Improving Attributed Text Generation with Self-Guided MCTS","venue":"ACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.acl-long.490/","topics":["citations","mcts","attribution"]},
    {"id":"rmm","first_public":"2025","title":"RMM: Reinforced Memory Management for Long-Term Conversational Agents","venue":"ACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.acl-long.413/","topics":["memory","conversation","reinforcement-learning"]},
    {"id":"mplus","first_public":"2025","title":"M+: Extending MemoryLLM with Scalable Long-Term Memory","venue":"ICML 2025","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v267/wang25au.html","topics":["latent-memory","retrieval"]},
    {"id":"comrag","first_public":"2025","title":"ComRAG: A Conversational Retrieval-Augmented Generation Framework with Dynamic Memory Consolidation","venue":"ACL Industry 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.acl-industry.53/","topics":["memory","consolidation","latency"]},
    {"id":"visrag","first_public":"2024-10-14","title":"VisRAG: Vision-based Retrieval-Augmented Generation on Multi-modality Documents","venue":"ICLR 2025","status":"peer-reviewed","primary_url":"https://proceedings.iclr.cc/paper_files/paper/2025/hash/3640e20b253c7530cce06abdd3c2361b-Abstract-Conference.html","topics":["visual-rag","documents","generation"]},
    {"id":"vdoc-rag","first_public":"2025","title":"Visual Document Retrieval-Augmented Generation with Dynamic Token Compression","venue":"CVPR 2025","status":"peer-reviewed","primary_url":"https://openaccess.thecvf.com/content/CVPR2025/html/Tanaka_Visual_Document_Retrieval-Augmented_Generation_with_Dynamic_Token_Compression_CVPR_2025_paper.html","topics":["visual-rag","compression"]},
    {"id":"molorag","first_public":"2025","title":"MoLoRAG: Bootstrapping VLM-Based Retrieval with a Multi-Modal Document Graph","venue":"EMNLP 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.emnlp-main.708/","topics":["visual-rag","graph","documents"]},
    {"id":"real-mm-rag","first_public":"2025","title":"REAL-MM-RAG: A Real-World Multi-Modal Retrieval Augmented Generation Benchmark","venue":"ACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.acl-long.1528/","topics":["multimodal","benchmark"]},
    {"id":"syftr","first_public":"2025","title":"syftr: Pareto-Optimal Generative AI","venue":"AutoML / PMLR 2025","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v293/conway25a.html","topics":["automl","pareto","cost"]},
    {"id":"grip","first_public":"2026","title":"Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning","venue":"ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.acl-long.196/","topics":["retrieval-control","generation","reinforcement-learning"]},
    {"id":"q-rag","first_public":"2025","title":"Q-RAG: Learning to Select Evidence with Value-Based Reinforcement Learning","venue":"ICLR 2026 Oral","status":"peer-reviewed","primary_url":"https://iclr.cc/virtual/2026/poster/10009944","topics":["retrieval-policy","value-learning","long-context"]},
    {"id":"deep-rag","first_public":"2025","title":"DeepRAG: Thinking to Retrieval Step by Step for Large Language Models","venue":"ICLR 2026","status":"peer-reviewed","primary_url":"https://iclr.cc/virtual/2026/poster/10009155","topics":["retrieval-policy","mdp","reasoning"]},
    {"id":"hiprag","first_public":"2025","title":"HiPRAG: Hierarchical Process Rewards for Retrieval-Augmented Generation","venue":"ICLR 2026","status":"peer-reviewed","primary_url":"https://iclr.cc/virtual/2026/poster/10010451","topics":["process-reward","search-efficiency"]},
    {"id":"knowledgeable-r1","first_public":"2025","title":"Knowledgeable-R1: Learning to Know When to Search and Trust External Knowledge","venue":"ICLR 2026","status":"peer-reviewed","primary_url":"https://iclr.cc/virtual/2026/poster/10011379","topics":["conflict","parametric-knowledge","reinforcement-learning"]},
    {"id":"ldar","first_public":"2025","title":"Learning Distraction-Aware Retrieval for Retrieval-Augmented Generation","venue":"ICLR 2026","status":"peer-reviewed","primary_url":"https://iclr.cc/virtual/2026/poster/10008538","topics":["distraction","evidence-utility","long-context"]},
    {"id":"ras","first_public":"2025","title":"Retrieval-Augmented Reasoning with Query-Specific Knowledge Graphs","venue":"ICLR 2026","status":"peer-reviewed","primary_url":"https://iclr.cc/virtual/2026/poster/10008199","topics":["dynamic-graph","reasoning"]},
    {"id":"when-graphs-rag","first_public":"2025","title":"When to Use Graphs in Retrieval-Augmented Generation","venue":"ICLR 2026","status":"peer-reviewed","primary_url":"https://iclr.cc/virtual/2026/poster/10007992","topics":["graph","benchmark","component-analysis"]},
    {"id":"routerag","first_public":"2026","title":"RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning","venue":"Findings ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.findings-acl.1502/","topics":["routing","graph","reinforcement-learning"]},
    {"id":"program-rag","first_public":"2026","title":"PROGRAM: Programmatic Retrieval Optimization with Generative Reasoning and Augmented Multi-queries","venue":"Findings ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.findings-acl.1090/","topics":["programmatic-retrieval","multi-hop"]},
    {"id":"proprag","first_public":"2025","title":"PropRAG: Guiding Retrieval with Beam Search over Proposition Paths","venue":"EMNLP 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.emnlp-main.317/","topics":["propositions","beam-search","multi-hop"]},
    {"id":"megarag","first_public":"2026","title":"MegaRAG: Multimodal Knowledge Graph Retrieval-Augmented Generation","venue":"ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.acl-long.2218/","topics":["multimodal","graph"]},
    {"id":"robust-visrag","first_public":"2026","title":"RobustVisRAG: Robust Retrieval-Augmented Generation for Real-World Visual Document Understanding","venue":"CVPR 2026","status":"peer-reviewed","primary_url":"https://openaccess.thecvf.com/content/CVPR2026/html/Zhang_RobustVisRAG_Robust_Retrieval-Augmented_Generation_for_Real-World_Visual_Document_Understanding_CVPR_2026_paper.html","topics":["visual-rag","robustness","distortion"]},
    {"id":"compactds","first_public":"2025","title":"Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks","venue":"ICLR 2026","status":"peer-reviewed","primary_url":"https://iclr.cc/virtual/2026/poster/10011084","topics":["datastore","systems","reasoning"]},
    {"id":"rag-rl","first_public":"2026","title":"Tackling Distractor Documents in Multi-Hop QA with Reinforcement and Curriculum Learning","venue":"Findings EACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.findings-eacl.294/","topics":["citations","curriculum","distractors"]},
    {"id":"ragas","first_public":"2023","title":"RAGAS: Automated Evaluation of Retrieval Augmented Generation","venue":"EACL 2024 Demo","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.eacl-demo.16/","topics":["evaluation","faithfulness"]},
    {"id":"ares","first_public":"2023","title":"ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems","venue":"NAACL 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.naacl-long.20/","topics":["evaluation","prediction-powered-inference"]},
    {"id":"rgb","first_public":"2023-09-04","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","venue":"AAAI 2024","status":"peer-reviewed","primary_url":"https://ojs.aaai.org/index.php/AAAI/article/view/29728","topics":["evaluation","noise","counterfactual"]},
    {"id":"crud-rag","first_public":"2024-01-30","title":"CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation","venue":"ACM TOIS","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/3701228","topics":["evaluation","crud","chinese"]},
    {"id":"ragtruth","first_public":"2023","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","venue":"ACL 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.acl-long.585/","topics":["hallucination","span-labels"]},
    {"id":"ragchecker","first_public":"2024","title":"RAGChecker: A Fine-Grained Framework for Diagnosing Retrieval-Augmented Generation","venue":"NeurIPS 2024 Datasets and Benchmarks","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2024/file/27245589131d17368cccdfa990cbf16e-Paper-Datasets_and_Benchmarks_Track.pdf","topics":["evaluation","claims","diagnostics"]},
    {"id":"crag-benchmark","first_public":"2024","title":"CRAG: A Comprehensive RAG Benchmark","venue":"NeurIPS 2024 Datasets and Benchmarks","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2024/hash/1435d2d0fca85a84d83ddcb754f58c29-Abstract-Datasets_and_Benchmarks_Track.html","topics":["benchmark","freshness","long-tail"]},
    {"id":"bright","first_public":"2024-07","title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","venue":"ICLR 2025","status":"peer-reviewed","primary_url":"https://proceedings.iclr.cc/paper_files/paper/2025/file/7a0f8055c838df8e62329a76c7c6403d-Paper-Conference.pdf","topics":["benchmark","reasoning-retrieval"]},
    {"id":"nomiracl","first_public":"2024","title":"NoMIRACL: Knowing When You Don't Know for Robust Multilingual Retrieval-Augmented Generation","venue":"Findings EMNLP 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.findings-emnlp.730/","topics":["multilingual","abstention","hallucination"]},
    {"id":"mtrag","first_public":"2025","title":"mt RAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","venue":"TACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.tacl-1.36/","topics":["multi-turn","benchmark"]},
    {"id":"garage","first_public":"2025","title":"GaRAGe: A Benchmark for Grounded and Reliable RAG Evaluation","venue":"Findings ACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.findings-acl.875/","topics":["grounding","deflection","citations"]},
    {"id":"longmemeval","first_public":"2024","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","venue":"ICLR 2025","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=pZiyCaVuti","topics":["memory","benchmark","updates"]},
    {"id":"trec-rag","first_public":"2024","title":"TREC Retrieval-Augmented Generation Track","venue":"NIST TREC 2024-2026","status":"benchmark-program","primary_url":"https://trec-rag.github.io/","topics":["benchmark","citations","external-judgments"]},
    {"id":"freshqa","first_public":"2023","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","venue":"Findings ACL 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.findings-acl.813/","topics":["freshness","search","dynamic-qa"]},
    {"id":"agentpoison","first_public":"2024","title":"AgentPoison: Red-Teaming LLM Agents via Poisoning Memory or Knowledge Bases","venue":"NeurIPS 2024","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2024/hash/eb113910e9c3f6242541c1652e30dfd6-Abstract-Conference.html","topics":["security","poisoning","backdoor"]},
    {"id":"poisonedrag","first_public":"2024","title":"PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models","venue":"USENIX Security 2025","status":"peer-reviewed","primary_url":"https://www.usenix.org/conference/usenixsecurity25/presentation/zou-poisonedrag","topics":["security","poisoning"]},
    {"id":"saferag","first_public":"2025","title":"SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model","venue":"ACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.acl-long.230/","topics":["security","benchmark","conflict"]},
    {"id":"rag-not-safer","first_public":"2025","title":"RAG LLMs Are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models","venue":"NAACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.naacl-long.281/","topics":["safety","robustness"]},
    {"id":"secon-rag","first_public":"2025","title":"SeCon-RAG: A Security-Conscious Retrieval-Augmented Generation Framework","venue":"NeurIPS 2025","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2025/hash/668563ef18fbfef0b66af491ea334d5f-Abstract-Conference.html","topics":["security","filtering","conflict"]},
    {"id":"c-rag-conformal","first_public":"2024","title":"C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models","venue":"ICML 2024","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v235/kang24a.html","topics":["conformal-risk","certification"]},
    {"id":"pra-rag","first_public":"2026","title":"PRA-RAG: Provably Robust Aggregation for Retrieval-Augmented Generation","venue":"Findings ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.findings-acl.1794/","topics":["security","provable-robustness","poisoning"]},
    {"id":"beir","first_public":"2021","title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models","venue":"NeurIPS 2021 Datasets and Benchmarks","status":"peer-reviewed","primary_url":"https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/65b9eea6e1cc6bb9f0cd2a47751a186f-Abstract-round2.html","topics":["retrieval","benchmark","zero-shot"]},
    {"id":"mteb","first_public":"2022","title":"MTEB: Massive Text Embedding Benchmark","venue":"EACL 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.eacl-main.148/","topics":["embeddings","benchmark"]},
    {"id":"mmteb","first_public":"2024","title":"MMTEB: Massive Multilingual Text Embedding Benchmark","venue":"ICLR 2025","status":"peer-reviewed","primary_url":"https://proceedings.iclr.cc/paper_files/paper/2025/file/fc0e3f908a2116ba529ad0a1530a3675-Paper-Conference.pdf","topics":["multilingual","embeddings","benchmark"]},
    {"id":"rocchio-1971","first_public":"1971","title":"Relevance Feedback in Information Retrieval","venue":"The SMART Retrieval System","status":"peer-reviewed","primary_url":"https://doi.org/10.1137/1.9781611971817.3","topics":["relevance-feedback","query-expansion"]},
    {"id":"relevance-models-2001","first_public":"2001","title":"Relevance-Based Language Models","venue":"SIGIR 2001","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/383952.383972","topics":["rm3","pseudo-relevance-feedback","language-model-retrieval"]},
    {"id":"rrf-2009","first_public":"2009","title":"Reciprocal Rank Fusion Outperforms Condorcet and Individual Rank Learning Methods","venue":"SIGIR 2009","status":"peer-reviewed","primary_url":"https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf","topics":["fusion","rrf"]},
    {"id":"texttiling","first_public":"1997","title":"TextTiling: Segmenting Text into Multi-Paragraph Subtopic Passages","venue":"Computational Linguistics","status":"peer-reviewed","primary_url":"https://aclanthology.org/J97-1003/","topics":["chunking","topic-segmentation"]},
    {"id":"layoutlmv3","first_public":"2022","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","venue":"ACM Multimedia 2022","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/3503161.3548112","topics":["document-ai","layout","multimodal"]},
    {"id":"nougat","first_public":"2023-08-25","title":"Nougat: Neural Optical Understanding for Academic Documents","venue":"ICLR 2024","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=fUtxNAKpdV","topics":["ocr","scientific-documents","parsing"]},
    {"id":"docling","first_public":"2024","title":"Docling Technical Report","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2408.09869","topics":["document-parsing","layout","tables"]},
    {"id":"pdf-to-tree","first_public":"2024","title":"PDF-to-Tree: Parsing PDF Content into a Tree Structure","venue":"Findings EMNLP 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.findings-emnlp.628/","topics":["pdf","parsing","hierarchy"]},
    {"id":"dense-x-retrieval","first_public":"2023-12","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","venue":"EMNLP 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.emnlp-main.845/","topics":["propositions","chunking","granularity"]},
    {"id":"late-chunking","first_public":"2024-09","title":"Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2409.04701","topics":["chunking","contextual-embeddings"]},
    {"id":"contextual-retrieval-anthropic","first_public":"2024","title":"Introducing Contextual Retrieval","venue":"Anthropic Engineering","status":"industry-report","primary_url":"https://www.anthropic.com/engineering/contextual-retrieval","topics":["contextual-retrieval","chunking","hybrid"]},
    {"id":"deepct","first_public":"2019","title":"Context-Aware Term Weighting for First Stage Passage Retrieval","venue":"SIGIR 2020","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/3397271.3401204","topics":["learned-sparse","term-weighting"]},
    {"id":"doc2query","first_public":"2019-04","title":"Document Expansion by Query Prediction","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/1904.08375","topics":["document-expansion","sparse-retrieval"]},
    {"id":"deepimpact","first_public":"2021-04","title":"Learning Passage Impacts for Inverted Indexes","venue":"CIKM 2021","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/3459637.3482273","topics":["learned-sparse","impact-index"]},
    {"id":"coil","first_public":"2021","title":"COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List","venue":"NAACL 2021","status":"peer-reviewed","primary_url":"https://aclanthology.org/2021.naacl-main.241/","topics":["learned-sparse","multi-vector","lexical"]},
    {"id":"splade-original","first_public":"2021","title":"SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking","venue":"SIGIR 2021","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/3404835.3463098","topics":["learned-sparse","expansion"]},
    {"id":"splade-plus-plus","first_public":"2022-05","title":"SPLADE++: Ensemble Distillation for High Performance Sparse Information Retrieval","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2205.04733","topics":["learned-sparse","distillation","hard-negatives"]},
    {"id":"wand","first_public":"2003","title":"Efficient Query Evaluation Using a Two-Level Retrieval Process","venue":"CIKM 2003","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/956863.956944","topics":["inverted-index","dynamic-pruning","wand"]},
    {"id":"block-max-wand","first_public":"2011","title":"Faster Top-k Document Retrieval Using Block-Max Indexes","venue":"SIGIR 2011","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/2009916.2010048","topics":["inverted-index","dynamic-pruning"]},
    {"id":"ance","first_public":"2020","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","venue":"ICLR 2021","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=zeFrfgyZln","topics":["dense-retrieval","ann-negatives","training"]},
    {"id":"rocketqa","first_public":"2020","title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","venue":"NAACL 2021","status":"peer-reviewed","primary_url":"https://aclanthology.org/2021.naacl-main.466/","topics":["dense-retrieval","denoising","cross-batch-negatives"]},
    {"id":"tas-balanced","first_public":"2021-04","title":"Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling","venue":"SIGIR 2021","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/3404835.3462891","topics":["dense-retrieval","distillation","sampling"]},
    {"id":"condenser","first_public":"2021","title":"Condenser: a Pre-training Architecture for Dense Retrieval","venue":"EMNLP 2021","status":"peer-reviewed","primary_url":"https://aclanthology.org/2021.emnlp-main.75/","topics":["dense-retrieval","pretraining"]},
    {"id":"cocondenser","first_public":"2021","title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval","venue":"ACL 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.acl-long.203/","topics":["dense-retrieval","pretraining","contrastive"]},
    {"id":"retromae","first_public":"2022","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","venue":"EMNLP 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.emnlp-main.35/","topics":["dense-retrieval","pretraining","masked-autoencoder"]},
    {"id":"simlm","first_public":"2022","title":"SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval","venue":"ACL 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.acl-long.125/","topics":["dense-retrieval","pretraining","bottleneck"]},
    {"id":"gpl","first_public":"2021","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","venue":"NAACL 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.naacl-main.168/","topics":["domain-adaptation","synthetic-queries","distillation"]},
    {"id":"gtr","first_public":"2021","title":"Large Dual Encoders Are Generalizable Retrievers","venue":"EMNLP 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.emnlp-main.669/","topics":["dense-retrieval","scaling","zero-shot"]},
    {"id":"e5","first_public":"2022-12","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2212.03533","topics":["embeddings","weak-supervision","contrastive"]},
    {"id":"instructor","first_public":"2022","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","venue":"Findings ACL 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.findings-acl.71/","topics":["embeddings","instructions"]},
    {"id":"dragon-retriever","first_public":"2023","title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval","venue":"Findings EMNLP 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.findings-emnlp.423/","topics":["dense-retrieval","augmentation","generalization"]},
    {"id":"colbert-original","first_public":"2020","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","venue":"SIGIR 2020","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/3397271.3401075","topics":["late-interaction","multi-vector"]},
    {"id":"plaid","first_public":"2022-05","title":"PLAID: An Efficient Engine for Late Interaction Retrieval","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2205.09707","topics":["late-interaction","indexing","efficiency"]},
    {"id":"xtr","first_public":"2023-04","title":"XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2304.01982","topics":["multi-vector","token-retrieval","efficiency"]},
    {"id":"citadel","first_public":"2023","title":"CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval","venue":"ACL 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.acl-long.663/","topics":["multi-vector","lexical-routing","efficiency"]},
    {"id":"hnsw","first_public":"2016","title":"Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs","venue":"IEEE TPAMI","status":"peer-reviewed","primary_url":"https://doi.org/10.1109/TPAMI.2018.2889473","topics":["ann","hnsw","vector-index"]},
    {"id":"product-quantization","first_public":"2011","title":"Product Quantization for Nearest Neighbor Search","venue":"IEEE TPAMI","status":"peer-reviewed","primary_url":"https://doi.org/10.1109/TPAMI.2010.57","topics":["ann","quantization","compression"]},
    {"id":"opq","first_public":"2013","title":"Optimized Product Quantization for Approximate Nearest Neighbor Search","venue":"CVPR 2013","status":"peer-reviewed","primary_url":"https://openaccess.thecvf.com/content_cvpr_2013/html/Ge_Optimized_Product_Quantization_2013_CVPR_paper.html","topics":["ann","quantization","rotation"]},
    {"id":"scann","first_public":"2020","title":"Accelerating Large-Scale Inference with Anisotropic Vector Quantization","venue":"ICML 2020","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v119/guo20h.html","topics":["ann","scann","quantization"]},
    {"id":"diskann","first_public":"2019","title":"DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node","venue":"NeurIPS 2019","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper/2019/hash/09853c7fb1d3f8ee67a61b6bf4a7f8e6-Abstract.html","topics":["ann","disk","vector-index"]},
    {"id":"spann","first_public":"2021","title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search","venue":"NeurIPS 2021","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2021/hash/299dc35e747eb77177d9cea10a802da2-Abstract.html","topics":["ann","disk","inverted-file"]},
    {"id":"faiss","first_public":"2017","title":"Billion-scale Similarity Search with GPUs","venue":"IEEE Big Data 2017","status":"peer-reviewed","primary_url":"https://arxiv.org/abs/1702.08734","topics":["ann","gpu","faiss"]},
    {"id":"worst-case-ann","first_public":"2023","title":"Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations","venue":"NeurIPS 2023","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2023/hash/d0ac28b79816b51124fcc804b2496a36-Abstract-Conference.html","topics":["ann","robustness","theory"]},
    {"id":"bert-reranking","first_public":"2019-01","title":"Passage Re-ranking with BERT","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/1901.04085","topics":["reranking","cross-encoder"]},
    {"id":"monot5","first_public":"2020","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","venue":"Findings EMNLP 2020","status":"peer-reviewed","primary_url":"https://aclanthology.org/2020.findings-emnlp.63/","topics":["reranking","t5","generative-ranking"]},
    {"id":"rankt5","first_public":"2023","title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","venue":"SIGIR 2023","status":"peer-reviewed","primary_url":"https://www.microsoft.com/en-us/research/publication/rankt5-fine-tuning-t5-for-text-ranking-with-ranking-losses/","topics":["reranking","listwise","ranking-loss"]},
    {"id":"rankgpt","first_public":"2023","title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","venue":"EMNLP 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.emnlp-main.923/","topics":["reranking","llm","listwise"]},
    {"id":"hyrr","first_public":"2024","title":"Hybrid Text Retrieval with Large Language Models: A Study of Robustness and Generalization","venue":"LREC-COLING 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.lrec-main.748/","topics":["reranking","hybrid","robustness"]},
    {"id":"setr","first_public":"2025","title":"Shifting from Ranking to Set Selection for Retrieval Augmented Generation","venue":"ACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.acl-long.861/","topics":["set-selection","multi-hop","reranking"]},
    {"id":"knowledge-selection-rag","first_public":"2025","title":"How Does Knowledge Selection Help Retrieval Augmented Generation?","venue":"Findings EMNLP 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.findings-emnlp.218/","topics":["selection","reranking","generation"]},
    {"id":"recomp","first_public":"2023-10","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","venue":"ICLR 2024","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=mlJLVigNHp","topics":["compression","selective-augmentation"]},
    {"id":"llmlingua","first_public":"2023","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","venue":"EMNLP 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.emnlp-main.825/","topics":["prompt-compression","efficiency"]},
    {"id":"longllmlingua","first_public":"2023","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","venue":"ACL 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.acl-long.91/","topics":["prompt-compression","long-context","position-bias"]},
    {"id":"llmlingua2","first_public":"2024","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","venue":"Findings ACL 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.findings-acl.57/","topics":["prompt-compression","distillation"]},
    {"id":"alce","first_public":"2023","title":"Enabling Large Language Models to Generate Text with Citations","venue":"EMNLP 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.emnlp-main.398/","topics":["citations","attributed-generation","benchmark"]},
    {"id":"rarr","first_public":"2022","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","venue":"ACL 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.acl-long.910/","topics":["verification","revision","attribution"]},
    {"id":"ircot","first_public":"2022","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","venue":"ACL 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.acl-long.557/","topics":["multi-hop","iterative-retrieval","reasoning"]},
    {"id":"self-ask","first_public":"2022","title":"Measuring and Narrowing the Compositionality Gap in Language Models","venue":"ICLR 2023","status":"peer-reviewed","primary_url":"https://openreview.net/forum?id=40yPtmzndN","topics":["self-ask","decomposition","search"]},
    {"id":"graftnet","first_public":"2018","title":"Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text","venue":"EMNLP 2018","status":"peer-reviewed","primary_url":"https://aclanthology.org/D18-1455/","topics":["knowledge-graph","text","graph-neural-network"]},
    {"id":"pullnet","first_public":"2019","title":"PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text","venue":"EMNLP-IJCNLP 2019","status":"peer-reviewed","primary_url":"https://aclanthology.org/D19-1242/","topics":["knowledge-graph","iterative-retrieval"]},
    {"id":"kg-fid","first_public":"2022","title":"KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering","venue":"ACL 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.acl-long.340/","topics":["knowledge-graph","fid","multi-hop"]},
    {"id":"tablerag","first_public":"2025","title":"TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning","venue":"EMNLP 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.emnlp-main.710/","topics":["tables","sql","heterogeneous-documents"]},
    {"id":"t2-ragbench","first_public":"2026","title":"T2-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generation","venue":"EACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.eacl-long.8/","topics":["tables","benchmark","numerical-reasoning"]},
    {"id":"t-rag-tables","first_public":"2026","title":"RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking","venue":"Findings ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.findings-acl.1902/","topics":["tables","hierarchical-index","graph"]},
    {"id":"ocr-rag-benchmark","first_public":"2026","title":"When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation","venue":"ACL Industry 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.acl-industry.60/","topics":["ocr","benchmark","document-rag"]},
    {"id":"scan-layout-rag","first_public":"2026","title":"SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation","venue":"Findings EACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.findings-eacl.82/","topics":["layout","visual-rag","document-parsing"]},
    {"id":"m3docvqa","first_public":"2025","title":"M3DocVQA: A Benchmark for Multi-Modal Multi-Document Question Answering","venue":"ICCV 2025 Workshop","status":"peer-reviewed","primary_url":"https://openaccess.thecvf.com/content/ICCV2025W/MIRU/html/Cho_M3DocVQA_A_Benchmark_for_Multi-Modal_Multi-Document_Question_Answering_ICCVW_2025_paper.html","topics":["multimodal","multi-document","benchmark"]},
    {"id":"docvqa","first_public":"2020","title":"DocVQA: A Dataset for VQA on Document Images","venue":"WACV 2021","status":"peer-reviewed","primary_url":"https://openaccess.thecvf.com/content/WACV2021/html/Mathew_DocVQA_A_Dataset_for_VQA_on_Document_Images_WACV_2021_paper.html","topics":["document-ai","visual-qa","benchmark"]},
    {"id":"chartqa","first_public":"2022","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","venue":"Findings ACL 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.findings-acl.177/","topics":["charts","visual-qa","reasoning"]},
    {"id":"privacy-good-bad","first_public":"2024","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation","venue":"Findings ACL 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.findings-acl.267/","topics":["privacy","extraction","rag"]},
    {"id":"multimodal-rag-privacy","first_public":"2025","title":"Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation","venue":"EMNLP 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.emnlp-main.1259/","topics":["privacy","multimodal","extraction"]},
    {"id":"graph-rag-privacy","first_public":"2026","title":"Exposing Privacy Risks in Graph Retrieval-Augmented Generation","venue":"Findings ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.findings-acl.899/","topics":["privacy","graph-rag","extraction"]},
    {"id":"private-retrieval-rag","first_public":"2024","title":"Don't Forget Private Retrieval: Distributed Private Similarity Search for Large Language Models","venue":"Privacy in NLP 2024","status":"peer-reviewed","primary_url":"https://aclanthology.org/2024.privatenlp-1.2/","topics":["privacy","mpc","similarity-search"]},
    {"id":"remoterag","first_public":"2025","title":"RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service","venue":"Findings ACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.findings-acl.197/","topics":["privacy","differential-privacy","cloud"]},
    {"id":"prompt-cache-audit","first_public":"2025","title":"Auditing Prompt Caching in Language Model APIs","venue":"ICML 2025","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v267/gu25b.html","topics":["caching","privacy","side-channel"]},
    {"id":"matryoshka-representation","first_public":"2022","title":"Matryoshka Representation Learning","venue":"NeurIPS 2022","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2022/hash/c32319f4868da7613d78af9993100e42-Abstract-Conference.html","topics":["embeddings","adaptive-dimension","efficiency"]},
    {"id":"adanns","first_public":"2023","title":"AdANNS: A Framework for Adaptive Semantic Search","venue":"NeurIPS 2023","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper_files/paper/2023/hash/f062da1973ac9ac61fc6d44dd7fa309f-Abstract-Conference.html","topics":["ann","adaptive-representation","efficiency"]},
    {"id":"ragbench","first_public":"2024","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2407.11005","topics":["benchmark","evaluation","trace"]},
    {"id":"hotpotqa","first_public":"2018","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","venue":"EMNLP 2018","status":"peer-reviewed","primary_url":"https://aclanthology.org/D18-1259/","topics":["multi-hop","benchmark","supporting-facts"]},
    {"id":"musique","first_public":"2021","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","venue":"TACL 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.tacl-1.31/","topics":["multi-hop","benchmark","composition"]},
    {"id":"2wikimultihopqa","first_public":"2020","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","venue":"COLING 2020","status":"peer-reviewed","primary_url":"https://aclanthology.org/2020.coling-main.580/","topics":["multi-hop","benchmark","reasoning"]},
    {"id":"asqa","first_public":"2022","title":"ASQA: Factoid Questions Meet Long-Form Answers","venue":"EMNLP 2022","status":"peer-reviewed","primary_url":"https://aclanthology.org/2022.emnlp-main.566/","topics":["long-form","ambiguous-qa","citations"]},
    {"id":"qampari","first_public":"2022-05","title":"QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2205.12665","topics":["list-qa","long-form","benchmark"]},
    {"id":"popqa","first_public":"2022","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","venue":"ACL 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.acl-long.546/","topics":["long-tail","parametric-memory","benchmark"]},
    {"id":"longbench","first_public":"2023-08","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2308.14508","topics":["long-context","benchmark","bilingual"]},
    {"id":"multihop-rag-benchmark","first_public":"2024-01","title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2401.15391","topics":["multi-hop","rag","benchmark"]},
    {"id":"r3ag-routing","first_public":"2026","title":"R3AG: Retriever Routing for Retrieval-Augmented Generation","venue":"ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.acl-long.939/","topics":["routing","retrievers","rag"]},
    {"id":"nest-retrieval","first_public":"2026","title":"NEST: Nested Evidence Survival for Retrieval","venue":"ACL Industry 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.acl-industry.35/","topics":["evidence-selection","noise","retrieval"]},
    {"id":"hichunk","first_public":"2026","title":"HiChunk: Evaluating and Enhancing Retrieval Augmented Generation with Hierarchical Chunking","venue":"ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.acl-long.1372/","topics":["chunking","hierarchical","evaluation"]},
    {"id":"dior","first_public":"2025","title":"DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation","venue":"ACL 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.acl-long.148/","topics":["dynamic-rag","retrieval-trigger","context-selection"]},
    {"id":"contextual-retriever-conversation","first_public":"2025","title":"Learning Contextual Retrieval for Robust Conversational Search","venue":"EMNLP 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.emnlp-main.602/","topics":["conversation","contextual-retrieval","embeddings"]},
    {"id":"stronger-lc-rag-baselines","first_public":"2025","title":"Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models","venue":"EMNLP 2025","status":"peer-reviewed","primary_url":"https://aclanthology.org/2025.emnlp-main.1656/","topics":["long-context","rag","baselines"]},
    {"id":"codepromptzip","first_public":"2026","title":"CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs","venue":"Findings ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.findings-acl.1384/","topics":["code","prompt-compression","rag"]},
    {"id":"repocoder","first_public":"2023-03","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","venue":"EMNLP 2023","status":"peer-reviewed","primary_url":"https://aclanthology.org/2023.emnlp-main.151/","topics":["code","iterative-retrieval","generation"]},
    {"id":"repoformer","first_public":"2024-03","title":"Repoformer: Selective Retrieval for Repository-Level Code Completion","venue":"ICML 2024","status":"peer-reviewed","primary_url":"https://proceedings.mlr.press/v235/wu24a.html","topics":["code","selective-retrieval","generation"]},
    {"id":"medrag","first_public":"2024-03","title":"MedRAG: Enhancing Large Language Models in Medicine with Retrieval-Augmented Generation","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2403.04115","topics":["medical","rag","domain"]},
    {"id":"raft","first_public":"2024-03","title":"RAFT: Adapting Language Model to Domain Specific RAG","venue":"arXiv","status":"preprint","primary_url":"https://arxiv.org/abs/2403.10131","topics":["domain-adaptation","fine-tuning","rag"]},
    {"id":"vllm","first_public":"2023","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","venue":"SOSP 2023","status":"peer-reviewed","primary_url":"https://doi.org/10.1145/3600006.3613165","topics":["serving","paged-attention","systems"]},
    {"id":"flashattention","first_public":"2022","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","venue":"NeurIPS 2022","status":"peer-reviewed","primary_url":"https://proceedings.neurips.cc/paper/2022/hash/67d57c32e20fd0a7a302cb81d36e40d5-Abstract-Conference.html","topics":["attention","efficiency","serving"]},
    {"id":"mtrageval","first_public":"2026","title":"SemEval-2026 Task 8: MTRAGEval - Evaluating Multi-Turn Retrieval-Augmented Generation","venue":"SemEval 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.semeval-1.447/","topics":["multi-turn","benchmark","retrieval"]},
    {"id":"region-r1","first_public":"2026","title":"Region-R1: Reinforcing Query-Side Region Cropping for Multi-Modal Re-Ranking","venue":"Findings ACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.findings-acl.510/","topics":["multimodal","reranking","reinforcement-learning"]},
    {"id":"dissecting-graphrag","first_public":"2026","title":"Dissecting GraphRAG: A Modular Analysis of Knowledge Structuring for Factoid Question Answering","venue":"TACL 2026","status":"peer-reviewed","primary_url":"https://aclanthology.org/2026.tacl-1.29/","topics":["graph-rag","ablation","evaluation"]},
    {"id":"prompt-injection-wild","first_public":"2026","title":"Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems","venue":"USENIX Security 2026","status":"peer-reviewed","primary_url":"https://www.usenix.org/system/files/conference/usenixsecurity26/sec26_prepub_chang.pdf","topics":["security","prompt-injection","retrieval"]}
  ]
}