{"slug": "micro-macro-retrieval-reducing-long-form-hallucination-in-large-language-models", "title": "Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models", "summary": "Researchers have introduced Micro-Macro Retrieval (M2R), a new framework designed to reduce hallucination in large language models during long-form text generation. The system addresses the problem of factual errors by ensuring key information remains close to model outputs, using a two-tier retrieval process that extracts coarse-grained evidence from external sources and fine-grained details from an internal reasoning repository. Tested across multiple benchmarks, M2R demonstrated significant improvements in factual accuracy, particularly in tasks requiring lengthy context processing.", "body_md": "arXiv:2605.28828v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/micro-macro-retrieval-reducing-long-form-hallucination-in-large-language-models", "canonical_source": "https://arxiv.org/abs/2605.28828", "published_at": "2026-05-29 04:00:00+00:00", "updated_at": "2026-05-29 04:24:25.083975+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "generative-ai", "ai-research", "machine-learning"], "entities": ["Micro-Macro Retrieval", "M2R", "Large Language Models", "LLMs", "Retrieval-Augmented Language Models", "RALMs"], "alternates": {"html": "https://wpnews.pro/news/micro-macro-retrieval-reducing-long-form-hallucination-in-large-language-models", "markdown": "https://wpnews.pro/news/micro-macro-retrieval-reducing-long-form-hallucination-in-large-language-models.md", "text": "https://wpnews.pro/news/micro-macro-retrieval-reducing-long-form-hallucination-in-large-language-models.txt", "jsonld": "https://wpnews.pro/news/micro-macro-retrieval-reducing-long-form-hallucination-in-large-language-models.jsonld"}}