mlsanityData to 7 Oct 2026

Feedback Adaptation for Retrieval-Augmented Generation

arXiv 2604.06647 ↗First posted 8 Apr 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems are typically evaluated under static assumptions, despite being frequently corrected through user or expert feedback in deployment. Existing evaluation protocols focus on overall accuracy and fail to capture how systems adapt after feedback is introduced. We introduce feedback adaptation as a problem setting for RAG systems, which asks how effectively and how quickly corrective feedback propagates to future queries. To make this behavior measurable, we propose two evaluation axes: correction lag, which captures the delay between feedback provision and behavioral change, and post-feedback performance, which measures reliability on semantically related queries after feedback. Using these metrics, we show that training-based approaches exhibit a trade-off between delayed correction and reliable adaptation. We further propose PatchRAG, a minimal inference-time instantiation that incorporates feedback without retraining, demonstrating immediate correction and strong post-feedback generalization under the proposed evaluation. Our results highlight feedback adaptation as a previously overlooked dimension of RAG system behavior in interactive settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 25 of its 35 references that are in the map. First posted on arXiv 8 Apr 2026.

Builds on

25 of 35 references.

References · 25

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  7. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  10. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  11. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  12. 2022Mass-Editing Memory in a Transformercited by 976
13 more
  1. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 571
  2. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  3. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 258
  4. 2019Document Expansion by Query Predictioncited by 225
  5. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  6. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  7. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
  8. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentationcited by 118
  9. 2023InstructRetro: Instruction Tuning post Retrieval-Augmented Pretrainingcited by 53
  10. 2024SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domainscited by 28
  11. 2024Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorizationcited by 15
  12. 2025Learning Contextual Retrieval for Robust Conversational Searchcited by 6
  13. 2025Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAGcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing LLMs through human feedback: a journey towards self-improvement
  2. 2025Test-time Corpus Feedback: From Retrieval to RAG
  3. 2025Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control
  4. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  5. 2026The RAT: A Unified Bayesian Model for RAG Evaluation
  6. 2026A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation
  7. 2025RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation
  8. 2024Toward Optimal Search and Retrieval for RAG