MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation

arXiv:2608.25085 · cs.CL · Submitted 2026-08-25 · Read on arXiv

cs.CL

Submitted: 2026-08-25

Updated: 2026-08-25

Code: https://github.com/piachouaifaty/MTDiag

Terminology

• Benchmark — 21× in this paper · explained in 2 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Emergency Department — 9× in this paper
• Provenance — 7× in this paper · explained in 4 episodes
• Ontology — 6× in this paper · explained in 2 episodes
• Hallucination — 5× in this paper · explained in 3 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Failure Modes — 3× in this paper · explained in 3 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Unified Medical Language System — 3× in this paper
• Benchmarking — 2× in this paper · explained in 3 episodes
• Beth Israel Deaconess Medical Center — 2× in this paper
• Core — 2× in this paper · explained in 2 episodes
• Intensive Care Unit — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Zero Data Retention — 2× in this paper
• Ablation — 1× in this paper · explained in 1 episode
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Modular Architecture — 1× in this paper · explained in 4 episodes
• Predictive Modeling — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes

Sources

• Language Models Change Facts Based on the Way You Talk
• MedGemma Technical Report
• MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation
• MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluation
• Flipping the Dialogue: Training and Evaluating User Language Models
• Benchmarking Benchmark Leakage in Large Language Models
• ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering