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

arXiv: https://arxiv.org/abs/2601.21551 · HTML: https://mlsanity.com/paper/2601.21551/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine](https://mlsanity.com/paper/2311.16452/) (2023)
- [BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains](https://mlsanity.com/paper/2402.10373/) (2024)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator](https://mlsanity.com/paper/2402.09742/) (2024)
- [DDXPlus: A New Dataset For Automatic Medical Diagnosis](https://mlsanity.com/paper/2205.09148/) (2022)
- [Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2505.19630/) (2025)
- [From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond](https://mlsanity.com/paper/2411.03590/) (2024)
- [MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis](https://mlsanity.com/paper/2502.19175/) (2025)
- [MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations](https://mlsanity.com/paper/2410.14204/) (2024)
- [Advancing Conversational Diagnostic AI with Multimodal Reasoning](https://mlsanity.com/paper/2505.04653/) (2025)
- [Towards Automatic Evaluation for LLMs' Clinical Capabilities: Metric, Data, and Algorithm](https://mlsanity.com/paper/2403.16446/) (2024)
- [Follow-up Question Generation For Enhanced Patient-Provider Conversations](https://mlsanity.com/paper/2503.17509/) (2025)
- [CliniChat: A Multi-Source Knowledge-Driven Framework for Clinical Interview Dialogue Reconstruction and Evaluation](https://mlsanity.com/paper/2504.10418/) (2025)
- [Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning](https://mlsanity.com/paper/2503.16463/) (2025)
- [DocCHA: Towards LLM-Augmented Interactive Online diagnosis System](https://mlsanity.com/paper/2507.07870/) (2025)

## Built on by (most cited first, 1 of 1)

- [ELICITED: EHR-grounded Longitudinal Interactive Conversations for Information-seeking Triage Evaluation and Decision-making](https://mlsanity.com/paper/2608.09024/) (2026)

## Abstract (arXiv)

Effective clinical history taking is a foundational yet underexplored component of clinical reasoning. While large language models (LLMs) have shown promise on static benchmarks, they often fall short in dynamic, multi-turn diagnostic settings that require iterative questioning and hypothesis refinement. To address this gap, we propose method, a note-driven framework that trains LLMs to conduct structured history taking and diagnosis by learning from widely available medical notes. Instead of relying on scarce and sensitive dialogue data, we convert real-world medical notes into high-quality doctor-patient dialogues using a decision tree-guided generation and refinement pipeline. We then propose a three-stage fine-tuning strategy combining supervised learning, simulated data augmentation, and preference learning. Furthermore, we propose a novel single-turn reasoning paradigm that reframes history taking as a sequence of single-turn reasoning problems. This design enhances interpretability and enables local supervision, dynamic adaptation, and greater sample efficiency. Experimental results show that our method substantially improves clinical reasoning, achieving gains of +16.9 F1 and +21.0 Top-1 diagnostic accuracy over GPT-4o. Our code and dataset can be found at https://github.com/zhentingsheng/Note2Chat.