AI Paper Atlas

Research map / Large language models / Agents, code and math

Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes

Yang Zhou, Zhenting Sheng, Mingrui Tan, Yuting Song, Jun Zhou, Yu Heng Kwan, Lian Leng Low, Yang Bai, Yong Liu

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 1 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 SFT on note-derived dialogues (ablation)Qwen2.5-7B-Instruct (multi-turn) · MIMIC-IV history takingaverage of six metrics: 37.5 -> 49.9Improved
add self-augmented trajectories from self-play rollouts (ablation)Note2Chat-MT · MIMIC-IV history takingaverage of six metrics: 49.9 -> 58.2Improved
add DPO with dialogue-level reward (ablation)Note2Chat-MT · MIMIC-IV history takingaverage of six metrics: 58.2 -> 60.6Improved
add DPO with dialogue-level reward (ablation)Note2Chat-MT · MIMIC-IV history taking#Turns: 15.8 -> 27.5Hurt
add SFT on note-derived dialogues (ablation)Note2Chat-ST · MIMIC-IV history takingaverage of six metrics: 37.5 -> 50.6Improved
add self-augmented trajectories (ablation)Note2Chat-ST · MIMIC-IV history takingaverage of six metrics: 50.6 -> 56.8Improved
add single-turn DPO with turn-level process reward (ablation)Note2Chat-ST · MIMIC-IV history takingaverage of six metrics: 56.8 -> 63.7Improved
add single-turn DPO with turn-level process reward (ablation)Note2Chat-ST · MIMIC-IV history taking#Turns: 20.5 -> 17.3Improved
use single-turn reasoning paradigm instead of multi-turn DPO (ablation)Note2Chat · MIMIC-IV history takingTop-1 accuracy: 62.0 -> 70.0Improved
use single-turn reasoning paradigm instead of multi-turn DPO (ablation)Note2Chat · MIMIC-IV history takingRecall: 55.4 -> 46.2Hurt
fine-tune with Note2Chat-ST pipelineQwen2.5-7B-Instruct · MIMIC-IV history takingF1: 19.6 -> 46.1Improved

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