# Think Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowledge Graphs

arXiv: https://arxiv.org/abs/2602.01995 · HTML: https://mlsanity.com/paper/2602.01995/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [Sequential Diagnosis with Language Models](https://mlsanity.com/paper/2506.22405/) (2025)
- [CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis](https://mlsanity.com/paper/2407.13301/) (2024)
- [Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator](https://mlsanity.com/paper/2403.08495/) (2024)
- [PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions](https://mlsanity.com/paper/2505.17818/) (2025)
- [Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators](https://mlsanity.com/paper/2501.09484/) (2025)
- [The Multi-Round Diagnostic RAG Framework for Emulating Clinical Reasoning](https://mlsanity.com/paper/2504.07724/) (2025)
- [MedKP: Medical Dialogue with Knowledge Enhancement and Clinical Pathway Encoding](https://mlsanity.com/paper/2403.06611/) (2024)
- [Retrieval-Augmented Chain-of-Thought in Semi-structured Domains](https://mlsanity.com/paper/2310.14435/) (2023)
- [Towards Faithful Knowledge Graph Explanation Through Deep Alignment in Commonsense Question Answering](https://mlsanity.com/paper/2310.04910/) (2023)
- [Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis](https://mlsanity.com/paper/2401.06541/) (2024)

## Abstract (arXiv)

Conversational diagnosis requires multi-turn history-taking, where an agent asks clarifying questions to refine differential diagnoses under incomplete information. Existing approaches often rely on the parametric knowledge of a model or assume that patients provide rich and concrete information, which is unrealistic. To address these limitations, we propose a conversational diagnosis system that explores a diagnostic knowledge graph to reason in two steps: (i) generating diagnostic hypotheses from the dialogue context, and (ii) verifying hypotheses through clarifying questions, which are repeated until a final diagnosis is reached. Since evaluating the system requires a realistic patient simulator that responds to the system's questions, we adopt PatientSim, a persona-driven patient simulator, together with patient profiles from MIMIC-IV. We further adapt it with low-specificity symptom reporting to reflect how real-world patients describe symptoms vaguely during early clinical encounters. Experiments show improved diagnostic accuracy and efficiency over strong baselines, and physician evaluations support the realism of our simulator and the clinical utility of the generated clarifying questions. Our code will be released upon publication.