AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Critic–Adviser–Reviser Cyclic Refinement: Towards High-Quality EMR Corpus Generation with LLMs

Chen Ning, Xien Liu, Chenwei Yan, Xiao Zhang, Xinxin You, Yuxuan Zhou, Xiangling Fu, Ji Wu

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Data and hallucination detection

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 Critic-Adviser-Reviser staged cyclic refinement to direct generationQwen2.5-7B-Instruct EMR generator · EMR qualitycontent completeness (%): 77.1 -> 91.2Improved
add stage-wise refinement instead of generic all-in-one Self-RefineEMR generator · EMR qualityknowledge coverage (%): 78.0 -> 94.1Improved
use LLM-CARe synthetic EMRs instead of MedSyn (real EMR text in context)downstream classifier · examination recommendationmicro accuracy (%): 82.9 -> 85.3Improved
add refinement to LLM generationQwen2.5-7B-Instruct · diagnosis predictionmicro accuracy (%): 81.8 -> 82.6No clear effect
add LLM-CARe on other backbones (Llama3.1, Meditron3, R1-Distill)LLM Direct · EMR quality (avg)average quality (%): 49.3 -> 77.5 (Llama3.1); 53.9 -> 76.4; 55.5 -> 80.5Improved
add each of Critic, Adviser and Reviser (ablation)LLM-CARe · EMR quality and downstream tasksquality and accuracyImproved
give initial draft generator a real EMR as example (ablation)LLM-CARe · EMR quality and downstream tasksquality and accuracyNo clear effect
add more than two refinement cycles per stage (ablation)LLM-CARe · EMR quality and downstream tasksquality and accuracyNo clear effect
use LLM-CARe on MIMIC-IV-Note (different institution)LLM-CARe vs LLM Direct · diagnosis prediction (MIMIC-IV-Note)macro accuracy: 0.532 -> 0.590Improved
use real EMR in-context examples (MedSyn) instead of quality-guided generationMedSyn · hospital course completenesscompletenessHurt

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