Guardado en:
Detalles Bibliográficos
Autores principales: Afolabi, Halimat, Afolabi, Zainab, Friel, Elizabeth, Roberts, Jude, Ji-Xu, Antonio, Chen, Lloyd, Ogbomo, Egheosa, Imevbore, Emiliomo, Eneje, Phil, Ouahidi, Wissal El, Sohal, Aaron, Kennan, Alisa, Srivastava, Shreya, Vairavan, Anirudh, Napitu, Laura, McClure, Katie
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.13988
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911672643354624
author Afolabi, Halimat
Afolabi, Zainab
Friel, Elizabeth
Roberts, Jude
Ji-Xu, Antonio
Chen, Lloyd
Ogbomo, Egheosa
Imevbore, Emiliomo
Eneje, Phil
Ouahidi, Wissal El
Sohal, Aaron
Kennan, Alisa
Srivastava, Shreya
Vairavan, Anirudh
Napitu, Laura
McClure, Katie
author_facet Afolabi, Halimat
Afolabi, Zainab
Friel, Elizabeth
Roberts, Jude
Ji-Xu, Antonio
Chen, Lloyd
Ogbomo, Egheosa
Imevbore, Emiliomo
Eneje, Phil
Ouahidi, Wissal El
Sohal, Aaron
Kennan, Alisa
Srivastava, Shreya
Vairavan, Anirudh
Napitu, Laura
McClure, Katie
contents Closed-source large language models (LLMs), such as ChatGPT and Gemini, are increasingly consulted for medical advice, yet their explanations may appear plausible while failing to reflect the model's underlying reasoning process. This gap poses serious risks as patients and clinicians may trust coherent but misleading explanations. We conduct a systematic black-box evaluation of faithfulness in medical reasoning among three widely used closed-source LLMs. Our study consists of three perturbation-based probes: (1) causal ablation, testing whether stated chain-of-thought (CoT) reasoning causally influences predictions; (2) positional bias, examining whether models create post-hoc justifications for answers driven by input positioning; and (3) hint injection, testing susceptibility to external suggestions. We complement these quantitative probes with a small-scale human evaluation of model responses to patient-style medical queries to examine concordance between physician assessments of explanation faithfulness and layperson perceptions of trustworthiness. We find that CoT reasoning steps often do not causally drive predictions, and models readily incorporate external hints without acknowledgment. In contrast, positional biases showed minimal impact in this setting. These results underscore that faithfulness, not just accuracy, must be central in evaluating LLMs for medicine, to ensure both public protection and safe clinical deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13988
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning
Afolabi, Halimat
Afolabi, Zainab
Friel, Elizabeth
Roberts, Jude
Ji-Xu, Antonio
Chen, Lloyd
Ogbomo, Egheosa
Imevbore, Emiliomo
Eneje, Phil
Ouahidi, Wissal El
Sohal, Aaron
Kennan, Alisa
Srivastava, Shreya
Vairavan, Anirudh
Napitu, Laura
McClure, Katie
Artificial Intelligence
Machine Learning
Closed-source large language models (LLMs), such as ChatGPT and Gemini, are increasingly consulted for medical advice, yet their explanations may appear plausible while failing to reflect the model's underlying reasoning process. This gap poses serious risks as patients and clinicians may trust coherent but misleading explanations. We conduct a systematic black-box evaluation of faithfulness in medical reasoning among three widely used closed-source LLMs. Our study consists of three perturbation-based probes: (1) causal ablation, testing whether stated chain-of-thought (CoT) reasoning causally influences predictions; (2) positional bias, examining whether models create post-hoc justifications for answers driven by input positioning; and (3) hint injection, testing susceptibility to external suggestions. We complement these quantitative probes with a small-scale human evaluation of model responses to patient-style medical queries to examine concordance between physician assessments of explanation faithfulness and layperson perceptions of trustworthiness. We find that CoT reasoning steps often do not causally drive predictions, and models readily incorporate external hints without acknowledgment. In contrast, positional biases showed minimal impact in this setting. These results underscore that faithfulness, not just accuracy, must be central in evaluating LLMs for medicine, to ensure both public protection and safe clinical deployment.
title Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.13988