mlsanityData to 7 Oct 2026

Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models

arXiv 2605.28828 ↗First posted 10 Apr 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contexts and lengthy reasoning chains amplify factual errors. Recent studies highlight a critical phenomenon: the closer key information appears to the model outputs, the higher the factual accuracy. However, existing retrieval-augmented language models (RALMs) lack effective mechanisms to ensure this proximity - external evidence is injected into reasoning via multi-turn retrieval, but this cannot ensure key information stays close to the outputs. We propose Micro-Macro Retrieval (M2R), a novel retrieve-while-generate framework to fill this gap. At the macro level, M2R retrieves coarse-grained evidence from external sources; at the micro level, it extracts essential results from a key information repository built during reasoning and reuses them while generating answers. This design directly addresses the key-information-to-output proximity bottleneck, effectively reducing hallucination in long-form tasks. M2R is trained with a curriculum learning-based reinforcement learning strategy using customized rule-based rewards, enabling stable acquisition of retrieval and grounding skills. Extensive experiments across different benchmarks demonstrate the effectiveness of M2R, especially in lengthy-context settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 57 of its 66 references that are in the map. First posted on arXiv 10 Apr 2026.

Builds on

57 of 66 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Measuring and Narrowing the Compositionality Gap in Language Models7 Oct

Other references · 56

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  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. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  8. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  9. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  10. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  11. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  12. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
38 more
  1. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  2. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  3. 2024Qwen2.5-Coder Technical Reportcited by 1,151
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  5. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  6. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  7. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  8. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  9. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  10. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  11. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 253
  12. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  13. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 165
  14. 2024Long-form factuality in large language modelscited by 146
  15. 2024Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapscited by 140
  16. 2024The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Modelscited by 87
  17. 2024RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generationcited by 75
  18. 2024Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encodingcited by 72
  19. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  20. 2025Steer LLM Latents for Hallucination Detectioncited by 49
  21. 2023Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuningcited by 45
  22. 2024DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLMcited by 45
  23. 2024Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Modelscited by 41
  24. 2023Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Trainingcited by 31
  25. 2025Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinkingcited by 29
  26. 2026Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RLcited by 27
  27. 2024Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arenacited by 26
  28. 2023Towards LLM-driven Dialogue State Trackingcited by 25
  29. 2025Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMscited by 25
  30. 2024Understanding Layer Significance in LLM Alignmentcited by 19
  31. 2024TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidationcited by 18
  32. 2025HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Modelscited by 17
  33. 2025AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agentcited by 17
  34. 2023How Good Are LLMs at Out-of-Distribution Detection?cited by 15
  35. 2024Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuningcited by 14
  36. 2025Recurrent Knowledge Identification and Fusion for Language Model Continual Learningcited by 14
  37. 2025Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarizationcited by 8
  38. 2023SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detectioncited by 7

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Disentangling Memory and Reasoning Ability in Large Language Models
  2. 2025HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
  3. 2025Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning
  4. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  5. 2025ConfRAG: Confidence-Guided Retrieval-Augmenting Generation
  6. 2026Adaptive Retrieval helps Reasoning in LLMs -- but mostly if it's not used
  7. 2024NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities
  8. 2024LargePiG: Your Large Language Model is Secretly a Pointer Generator