mlsanityData to 7 Oct 2026

RAG robustness and adaptive retrieval

589 papers2 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: rag, generation, retrieval, retrieval-augmented, llms

Key facts. RAG robustness and adaptive retrieval: 589 papers on arXiv since 2021 (data through 7 Oct 2026). 199 of its 589 mapped papers (34%) cite “Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection” (2023, arXiv 2310.11511). 61 of its 589 mapped papers (10%) cite “Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity” (2024, arXiv 2403.14403). 12 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

12 new papers, 17 Sep – 7 Oct; 2 this week.

  1. This week · 2
  2. Finding the Right Balance: Relevance and Diversity in LLM Retrieval also fits: Generation and context integration
  3. Tool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek also fits: RAG pipeline design and evaluation
  4. Earlier · 10
  5. RAGStress: A controlled benchmark for evaluating retrieval-augmented generation under knowledge-base degradation also fits: RAG pipeline design and evaluation
  6. Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering also fits: Generation and context integration
  7. Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction also fits: RAG pipeline design and evaluation
  8. Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generation
  9. Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG
  10. Regime Boundary Alignment for Evidence-Gated Question Answering
  11. Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers also fits: Medical and biomedical RAG
  12. Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented Generation
All 12
  1. To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech also fits: Conversational and speech RAG
  2. Bridging Static and Agentic RAG for Taiwanese Historical Question Answering also fits: Agentic RAG, agents and memory

Foundations

Most cited by papers here

  1. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection2023cited by 199 here
  2. Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity2024cited by 61 here
  3. Benchmarking Large Language Models in Retrieval-Augmented Generation2023cited by 42 here
  4. Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models2024cited by 29 here
  5. Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training2024cited by 27 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 153 here
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 420 here
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 97 here
  4. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 29 here
  5. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 94 here
  6. 2023In-Context Retrieval-Augmented Language Modelscited by 74 here
  7. 2023Active Retrieval Augmented Generationcited by 57 here
  8. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 80 here
  9. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 199 here
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 114 here
  11. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 40 here
13 more it builds on, not in this chain
  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 111 here
  2. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 38 here
  3. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 42 here
  4. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 40 here
  5. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 28 here
  6. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 33 here
  7. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 51 here
  8. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 35 here
  9. 2024Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Modelscited by 29 here
  10. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 61 here
  11. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 27 here
  12. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 27 here
  13. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 36 here

The 24 most cited of 718.

Browse

30 of 589, ranked 6–35

  1. 6InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales202422
  2. 7Retrieval-Augmented Generation with Conflicting Evidence202519
  3. 8RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation202417
  4. 9ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence202417
  5. 10Trustworthiness in Retrieval-Augmented Generation Systems: A Survey202417
  6. 11Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering202216
  7. 12Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models202415
  8. 13MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents202414
  9. 14FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"202414
  10. 15End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering202113
All 30
  1. 16Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models202512
  2. 17Sufficient Context: A New Lens on Retrieval Augmented Generation Systems202410
  3. 18FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation20259
  4. 19ChatQA: Surpassing GPT-4 on Conversational QA and RAG20249
  5. 20WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia20249
  6. 21SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation20249
  7. 22Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise20239
  8. 23BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering20248
  9. 24RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback20248
  10. 25Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation20248
  11. 26RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering20248
  12. 27Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems20248
  13. 28Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home20257
  14. 29Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases20247
  15. 30Are Large Language Models Good at Utility Judgments?20247
  16. 31Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation20247
  17. 32The Distracting Effect: Understanding Irrelevant Passages in RAG20256
  18. 33Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents20246
  19. 34CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG20246
  20. 35Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation20246