mlsanityData to 7 Oct 2026

RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback

arXiv 2403.06840 ↗First posted 11 Mar 2024cs.CL cs.AIcited by 46

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

Abstract (arXiv)

Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if irrelevant texts are retrieved, it may impair model performance. In this paper, we propose Retrieval Augmented Iterative Self-Feedback (RA-ISF), a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model's problem-solving capabilities. Experiments show that our method outperforms existing benchmarks, performing well on models like GPT3.5, Llama2, significantly enhancing factual reasoning capabilities and reducing hallucinations.

Key facts. Cited by 46 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 28 of its 36 references that are in the map. First posted on arXiv 11 Mar 2024.

Builds on

28 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  11. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  12. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
15 more
  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  3. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  4. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  5. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  6. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  7. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  8. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  9. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 290
  10. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  11. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  12. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
  13. 2020Unsupervised Question Decomposition for Question Answeringcited by 118
  14. 2023Understanding Retrieval Augmentation for Long-Form Question Answeringcited by 45
  15. 2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 17; 2025: 22; 2026: 7.

46 papers.

Sort:

By area:

  1. 2024BioRAG: A RAG-LLM Framework for Biological Question Reasoningcited by 42
  2. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  3. 2024Tool-Planner: Task Planning with Clusters across Multiple Toolscited by 32
  4. 2024Teola: Towards End-to-End Optimization of LLM-based Applicationscited by 32
  5. 2025SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinementcited by 27
  6. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfacescited by 24
  7. 2024ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systemscited by 22
  8. 2024Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspectivecited by 20
  9. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledgecited by 20
  10. 2024SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedbackcited by 19
  11. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaborationcited by 19
  12. 2024Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Frameworkcited by 12
34 more
  1. 2025KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generationcited by 12
  2. 2024CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversitycited by 11
  3. 2024Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generationcited by 11
  4. 2025LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridizationcited by 10
  5. 2025Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAGcited by 9
  6. 2025Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalizationcited by 9
  7. 2024Unified Active Retrieval for Retrieval Augmented Generationcited by 8
  8. 2024Retrieval-Augmented Machine Translation with Unstructured Knowledgecited by 8
  9. 2024Defining Knowledge: Bridging Epistemology and Large Language Modelscited by 7
  10. 2024Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applicationscited by 6
  11. 2025Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approachcited by 6
  12. 2025Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answeringcited by 6
  13. 2025Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP Documentscited by 5
  14. 2025IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generationcited by 4
  15. 2025GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learningcited by 4
  16. 2025Retrieval-Augmented Generation by Evidence Retroactivity in LLMscited by 3
  17. 2025Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answeringcited by 3
  18. 2025Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant Knowledgecited by 3
  19. 2024SRSA: A Cost-Efficient Strategy-Router Search Agent for Real-world Human-Machine Interactionscited by 2
  20. 2025Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selectioncited by 2
  21. 2024CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Object Detection under Unknown Degradationscited by 1
  22. 2024A Survey of Query Optimization in Large Language Modelscited by 1
  23. 2025ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generationcited by 1
  24. 2025Enhancing Coreference Resolution with Pretrained Language Models: Bridging the Gap Between Syntax and Semanticscited by 1
  25. 2025HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 1
  26. 2026D2Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoningcited by 1
  27. 2026A Reference Architecture for Agentic Hybrid Retrieval in Dataset Searchcited by 1
  28. 2025Accelerating Causal Network Discovery of Alzheimer Disease Biomarkers via Scientific Literature-based Retrieval Augmented Generationcited by 0
  29. 2025Learning to Trust: Dynamic Utilization of Retrieval-Augmented Generation for E-commerce Search Relevancecited by 0
  30. 2025Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generationcited by 0
  31. 2026When should I search more: Adaptive Complex Query Optimization with Reinforcement Learningcited by 0
  32. 2026HaS: Accelerating RAG through Homology-Aware Speculative Retrievalcited by 0
  33. 2026DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understandingcited by 0
  34. 2026An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistencycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models
  2. 2025SKILL-RAG: Self-Knowledge Induced Learning and Filtering for Retrieval-Augmented Generation
  3. 2025Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation
  4. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
  5. 2024Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems
  6. 2024Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning
  7. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  8. 2023Self-Knowledge Guided Retrieval Augmentation for Large Language Models