Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models
Large language models suffer from hallucination in long-form generation. Existing retrieval-augmented models cannot ensure key information stays close to outputs. This paper proposes Micro-Macro Retrieval (M2R), a retrieve-while-generate framework that retrieves coarse-grained evidence externally and extracts key information from a reasoning-built repository, significantly reducing hallucination. It uses curriculum learning-based reinforcement learning for stable training.
Article intelligence
Key points
- LLMs are prone to hallucination in long-form generation due to redundant context and long reasoning chains
- Factual accuracy increases when key information is closer to model outputs
- M2R uses macro-level and micro-level retrieval to maintain key-information proximity
- Curriculum learning-based reinforcement learning enables stable acquisition of retrieval and grounding skills
Why it matters
This matters because lLMs are prone to hallucination in long-form generation due to redundant context and long reasoning chains.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.28828] Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models
[Submitted on 10 Apr 2026]
Title:Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models
View a PDF of the paper titled Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models, by Yujie Feng and 9 other authors
View PDF HTML (experimental)
Abstract: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.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.28828 [cs.CL]
(or arXiv:2605.28828v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.28828
arXiv-issued DOI via DataCite
Submission history
From: Yujie Feng [view email] [v1] Fri, 10 Apr 2026 05:49:19 UTC (2,050 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models, by Yujie Feng and 9 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-05
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)