mlsanityData to 7 Oct 2026

Learning to Filter Context for Retrieval-Augmented Generation

arXiv 2311.08377 ↗First posted 14 Nov 2023cs.CL cs.AIcited by 82

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

On-the-fly retrieval of relevant knowledge has proven an essential element of reliable systems for tasks such as open-domain question answering and fact verification. However, because retrieval systems are not perfect, generation models are required to generate outputs given partially or entirely irrelevant passages. This can cause over- or under-reliance on context, and result in problems in the generated output such as hallucinations. To alleviate these problems, we propose FILCO, a method that improves the quality of the context provided to the generator by (1) identifying useful context based on lexical and information-theoretic approaches, and (2) training context filtering models that can filter retrieved contexts at test time. We experiment on six knowledge-intensive tasks with FLAN-T5 and LLaMa2, and demonstrate that our method outperforms existing approaches on extractive question answering (QA), complex multi-hop and long-form QA, fact verification, and dialog generation tasks. FILCO effectively improves the quality of context, whether or not it supports the canonical output.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 30 of its 41 references that are in the map. First posted on arXiv 14 Nov 2023.

Builds on

30 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks16 Dec

Other references · 29

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  7. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  10. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  11. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  12. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
17 more
  1. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  2. 2019Passage Re-ranking with BERTcited by 629
  3. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  4. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  5. 2019ELI5: Long Form Question Answeringcited by 567
  6. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  7. 2016NewsQA: A Machine Comprehension Datasetcited by 330
  8. 2020Nearest Neighbor Machine Translationcited by 209
  9. 2020GSum: A General Framework for Guided Neural Abstractive Summarizationcited by 129
  10. 2021Decontextualization: Making Sentences Stand-Alonecited by 101
  11. 2019Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answeringcited by 96
  12. 2022Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehensioncited by 79
  13. 2022Neuro-Symbolic Language Modeling with Automaton-augmented Retrievalcited by 60
  14. 2021Measuring and Increasing Context Usage in Context-Aware Machine Translationcited by 48
  15. 2021Phrase Retrieval Learns Passage Retrieval, Toocited by 33
  16. 2021Rider: Reader-Guided Passage Reranking for Open-Domain Question Answeringcited by 28
  17. 2014Deep Learning for Answer Sentence Selectioncited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 39; 2025: 24; 2026: 16.

82 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  3. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  4. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257
  5. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  6. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
  7. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 176
  8. 2024CodeRAG-Bench: Can Retrieval Augment Code Generation?cited by 89
  9. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  10. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  11. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
  12. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 76
38 more
  1. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generationcited by 63
  2. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 57
  3. 2024Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Surveycited by 50
  4. 2024Efficient Prompting Methods for Large Language Models: A Surveycited by 46
  5. 2024How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?cited by 44
  6. 2025Reducing Cost of LLM Agents with Trajectory Reductioncited by 44
  7. 2024UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysiscited by 40
  8. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  9. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewardscited by 33
  10. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directionscited by 30
  11. 2024Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generationcited by 27
  12. 2024Retrieval-augmented generation in multilingual settingscited by 27
  13. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAGcited by 26
  14. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Modelscited by 25
  15. 2025Provence: efficient and robust context pruning for retrieval-augmented generationcited by 25
  16. 2024Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMscited by 24
  17. 2024Claim Verification in the Age of Large Language Models: A Surveycited by 23
  18. 2023Align on the Fly: Adapting Chatbot Behavior to Established Normscited by 22
  19. 2023Towards Verifiable Text Generation with Evolving Memory and Self-Reflectioncited by 21
  20. 2025PISCO: Pretty Simple Compression for Retrieval-Augmented Generationcited by 20
  21. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarkingcited by 17
  22. 2026Learning Personalized Agents from Human Feedbackcited by 16
  23. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answeringcited by 14
  24. 2025Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Teamcited by 13
  25. 2024Grounding Language Models for Visual Entity Recognitioncited by 12
  26. 2024Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generationcited by 12
  27. 2024On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Modelscited by 10
  28. 2024Understanding Retrieval Robustness for Retrieval-Augmented Image Captioningcited by 9
  29. 2024A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoningcited by 8
  30. 2026Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inferencecited by 8
  31. 2024Chain of Evidences and Evidence to Generate: Prompting for Context Grounded and Retrieval Augmented Reasoningcited by 7
  32. 2024Hierarchical Indexing for Retrieval-Augmented Opinion Summarizationcited by 7
  33. 2024QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compressioncited by 7
  34. 2025Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retentioncited by 7
  35. 2026SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directionscited by 7
  36. 2025Passage Segmentation of Documents for Extractive Question Answeringcited by 6
  37. 2025Influence Guided Context Selection for Effective Retrieval-Augmented Generationcited by 6
  38. 2024DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generationcited by 5

50 most cited of 82 All 82 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Context Quality Matters in Training Fusion-in-Decoder for Extractive Open-Domain Question Answering
  2. 2025Dynamic Context Selection for Retrieval-Augmented Generation: Mitigating Distractors and Positional Bias
  3. 2024Context Awareness Gate For Retrieval Augmented Generation
  4. 2025Improving Context Fidelity via Native Retrieval-Augmented Reasoning
  5. 2024Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering
  6. 2024Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
  7. 2024RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering
  8. 2025On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems