AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

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

Yujie Feng, Jian Li, Zhihan Zhou, Pengfei Xu, Yujia Zhang, xiaoyu li, Xiaohui Zhou, Alan Zhao, Xi Chen, Xiao-Ming Wu

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Long-context and personalized retrieval · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add micro retrieval over key-information repository to ReSearch-style macro retrievalReSearch (Qwen2.5-7B) · Multi-hop QA (4 benchmarks)EM: HotpotQA 43.52 -> 44.11; MuSiQue 22.30 -> 24.12Improved
add micro retrieval to ReSearchReSearch (Qwen2.5-3B) · HotpotQAEM: 38.78 -> 38.70No clear effect
add micro retrieval to ReSearchReSearch (Qwen2.5-3B) · MuSiQueEM: 19.40 -> 20.87Improved
on-demand micro retrieval instead of one-shot grounding (ablation)M2R (7B) · MuSiQueEM: 23.38 -> 24.12Improved
two-stage curriculum instead of direct joint optimization (ablation)M2R (3B) · HotpotQAEM: 13.2 -> 38.7Improved
two-stage curriculum instead of direct joint optimization (ablation)M2R (3B) · MuSiQueEM: 3.9 -> 20.9Improved
add micro retrieval vs ReSearch on 5 concatenated questionsM2R (5Q) · MuSiQue-5QEM: 5.7 -> 8.4Improved
add micro retrieval vs ReSearch on other model familiesM2R · Bamboogle (Llama-3.1-8B)EM: 43.1 -> 42.9No clear effect
add micro retrieval vs ReSearch on Mistral-7BM2R · MuSiQue (Mistral-7B)EM: 23.7 -> 25.5Improved
add micro retrievalM2R · Inference latency (HotpotQA, 3B)inference time (s): ~4.3 -> ~4.7Hurt
vary retrieve top-k 3/5/8 (ablation)M2R · 2Wiki (3B)EM: 38.3 / 40.1 / 39.4No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy