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

Monica Munnangi, Saiph Savage
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:1340-1366, 2026.

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 \datasetname, 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 r/AskDocs. This dataset enables systematic evaluation of whether models can detect and correct misconceptions under a multi-turn context. We evaluate five state-of-the-art 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 approximately 50% within two follow-ups. Additionally, GPT-4o exhibits a sharper decline, falling from 65% to 21%, indicating a failure to sustain safe reasoning across dialogue. 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. These findings reveal a critical reliability gap in LLMs. Even when models tend to correct misconceptions initially, their performance degrades substantially over subsequent turns, leading to inconsistent and potentially unsafe guidance in patient-facing settings and highlighting the need for evaluation frameworks that capture multi-turn behavior.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-munnangi26a, title = {Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations}, author = {Munnangi, Monica and Savage, Saiph}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {1340--1366}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/munnangi26a/munnangi26a.pdf}, url = {https://proceedings.mlr.press/v340/munnangi26a.html}, 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 \datasetname, 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 r/AskDocs. This dataset enables systematic evaluation of whether models can detect and correct misconceptions under a multi-turn context. We evaluate five state-of-the-art 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 approximately 50% within two follow-ups. Additionally, GPT-4o exhibits a sharper decline, falling from 65% to 21%, indicating a failure to sustain safe reasoning across dialogue. 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. These findings reveal a critical reliability gap in LLMs. Even when models tend to correct misconceptions initially, their performance degrades substantially over subsequent turns, leading to inconsistent and potentially unsafe guidance in patient-facing settings and highlighting the need for evaluation frameworks that capture multi-turn behavior.} }
Endnote
%0 Conference Paper %T Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations %A Monica Munnangi %A Saiph Savage %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-munnangi26a %I PMLR %P 1340--1366 %U https://proceedings.mlr.press/v340/munnangi26a.html %V 340 %X 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 \datasetname, 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 r/AskDocs. This dataset enables systematic evaluation of whether models can detect and correct misconceptions under a multi-turn context. We evaluate five state-of-the-art 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 approximately 50% within two follow-ups. Additionally, GPT-4o exhibits a sharper decline, falling from 65% to 21%, indicating a failure to sustain safe reasoning across dialogue. 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. These findings reveal a critical reliability gap in LLMs. Even when models tend to correct misconceptions initially, their performance degrades substantially over subsequent turns, leading to inconsistent and potentially unsafe guidance in patient-facing settings and highlighting the need for evaluation frameworks that capture multi-turn behavior.
APA
Munnangi, M. & Savage, S.. (2026). Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:1340-1366 Available from https://proceedings.mlr.press/v340/munnangi26a.html.

Related Material