Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations

• URL: http://arxiv.org/abs/2607.12884v1
• Date: Tue, 14 Jul 2026 15:30:37 GMT
• Title: Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations
• Abstract summary: ThReadMed-QA is a multi-turn medical dialogue dataset of 2,437 patient-physician conversation threads.<n>This dataset enables systematic evaluation of whether models can detect and correct misconceptions under a multi-turn context.<n>Our experiments reveal a consistent pattern: even frontier models that can address misconceptions in a single interaction degrade substantially over subsequent turns.
• Score: 5.63130104359934
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Patients seeking medical information often ask questions that embed incorrect assumptions or misconceptions. In such cases, safe medical communication requires not only answering the question, but identifying and correcting the underlying false belief. These interactions naturally unfold over multiple turns, a pattern now mirrored in interactions with LLMs. Yet current evaluation frameworks do not capture model behavior in these settings, where misconceptions can emerge, persist, or evolve over the course of a conversation. Whether LLMs can reliably correct such misconceptions over time remains largely unexamined. To study this, we introduce ThReadMed-QA, a multi-turn medical dialogue dataset of 2,437 patient-physician conversation threads comprising 8,204 question-answer pairs, derived from real patient interactions on AskDocs. This dataset enables systematic evaluation of whether models can detect and correct misconceptions under a multi-turn context. We evaluate five LLMs using a rubric-based LLM-as-a-Judge framework that scores responses based on their ability to identify and correct misconceptions. Our experiments reveal a consistent pattern: even frontier models that can address misconceptions in a single interaction degrade substantially over subsequent turns. GPT-5 and Claude-Haiku correct these false presuppositions around 85% on initial questions but drop to roughly 50% within two follow-ups. An oracle analysis replacing prior model outputs with physician responses shows that much of the degradation is driven by error propagation, while performance remains imperfect even under correct context. Even when models tend to correct misconceptions initially, their performance degrades substantially over later turns, leading to inconsistent and potentially unsafe guidance in patient-facing settings and highlighting the need for evaluation frameworks that capture multi-turn behavior.

Related papers

• Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery [95.44432473367836]
  Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured.<n>We introduce Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discnative, and testable hypothesis spaces from inconclusive evidence.<n>We introduce HypoArena, comprising HypoData, a benchmark of 988 cases across six scientific and analytical domains, and HypoEval, an evaluation framework for open-ended hypothesis sets.
  arXiv  Detail & Related papers  (2026-07-17T08:56:43Z)
• This Treatment Works, Right? Evaluating LLM Sensitivity to Patient Question Framing in Medical QA [35.372014797343546]
  Large language models (LLMs) are sensitive to prompt phrasings and can be influenced by the way questions are worded.<n>We investigate this through a systematic evaluation in a controlled retrieval-augmented generation (RAG) setting for medical question answering (QA)<n>We construct a dataset of 6,614 query pairs grounded in clinical trial abstracts and evaluate response consistency across eight LLMs.
  arXiv  Detail & Related papers  (2026-04-06T18:03:54Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• Beyond Idealized Patients: Evaluating LLMs under Challenging Patient Behaviors in Medical Consultations [2.337503919179969]
  We study challenging patient behaviors that commonly arise in real medical consultations.<n>For each behavior, we specify concrete failure criteria that capture unsafe responses.<n>We evaluate a range of open- and closed-source LLMs on their responses to challenging patient utterances.
  arXiv  Detail & Related papers  (2026-03-31T07:42:07Z)
• Same Verdict, Different Reasons: LLM-as-a-Judge and Clinician Disagreement on Medical Chatbot Completeness [49.2667937337333]
  We stress-test this assumption for detecting incomplete patient-facing medical responses.<n>We evaluate three granularities (General-Likert, Analytical-Rubric, Dynamic-Checklist) and three backbone models across two clinician-annotated datasets.
  arXiv  Detail & Related papers  (2026-03-26T19:01:55Z)
• ThReadMed-QA: A Multi-Turn Medical Dialogue Benchmark from Real Patient Questions [5.63130104359934]
  ThReadMed-QA is a benchmark of 2,437 fully-answered patient-seeking conversation threads extracted from r/AskDocs.<n>We evaluate five state-of-the-art LLMs on a stratified test split of 238 conversations.<n>Even the strongest model, GPT-5, achieves only 41.2% fully-correct responses.
  arXiv  Detail & Related papers  (2026-03-11T20:17:57Z)
• When Metrics Disagree: Automatic Similarity vs. LLM-as-a-Judge for Clinical Dialogue Evaluation [18.338933046286257]
  Large language models (LLMs) are increasingly employed to address diverse problems, including medical queries.<n>LLMs often perform poorly in medical contexts, potentially leading to harmful misguidance for users.<n>This paper focuses on fine-tuning the Llama 2 7B, a transformer-based, decoder-only model, using transcripts from real patient-doctor interactions.
  arXiv  Detail & Related papers  (2026-02-27T21:09:43Z)
• M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding [66.78251988482222]
  Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning.<n>Current benchmarks for medical image understanding generally focus on the final answer while ignoring the reasoning path.<n>M3CoTBench aims to foster the development of transparent, trustworthy, and diagnostically accurate AI systems for healthcare.
  arXiv  Detail & Related papers  (2026-01-13T17:42:27Z)
• Shallow Robustness, Deep Vulnerabilities: Multi-Turn Evaluation of Medical LLMs [9.291589998223696]
  We introduce MedQA-Followup, a framework for evaluating multi-turn robustness in medical question answering.<n>Using controlled interventions on the MedQA dataset, we evaluate five state-of-the-art LLMs.<n>We find that while models perform reasonably well under shallow perturbations, they exhibit severe vulnerabilities in multi-turn settings.
  arXiv  Detail & Related papers  (2025-10-14T08:04:18Z)
• Structured Outputs Enable General-Purpose LLMs to be Medical Experts [50.02627258858336]
  Large language models (LLMs) often struggle with open-ended medical questions.<n>We propose a novel approach utilizing structured medical reasoning.<n>Our approach achieves the highest Factuality Score of 85.8, surpassing fine-tuned models.
  arXiv  Detail & Related papers  (2025-03-05T05:24:55Z)
• Uncertainty Estimation of Large Language Models in Medical Question Answering [60.72223137560633]
  Large Language Models (LLMs) show promise for natural language generation in healthcare, but risk hallucinating factually incorrect information. We benchmark popular uncertainty estimation (UE) methods with different model sizes on medical question-answering datasets. Our results show that current approaches generally perform poorly in this domain, highlighting the challenge of UE for medical applications.
  arXiv  Detail & Related papers  (2024-07-11T16:51:33Z)
• "Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation [90.09260023184932]
  Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) output by leveraging external knowledge sources to reduce factual hallucinations. NoMIRACL is a human-annotated dataset for evaluating LLM robustness in RAG across 18 typologically diverse languages. We measure relevance assessment using: (i) hallucination rate, measuring model tendency to hallucinate, when the answer is not present in passages in the non-relevant subset, and (ii) error rate, measuring model inaccuracy to recognize relevant passages in the relevant subset.
  arXiv  Detail & Related papers  (2023-12-18T17:18:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.