Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Zijie, Zhao, Xinyu, Peng, Jie, Zhu, Zhuangdi, Chen, Qingyu, Xu, Kaidi, Hu, Xia, Chen, Tianlong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2501.17860
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908844793266176
author Liu, Zijie
Zhao, Xinyu
Peng, Jie
Zhu, Zhuangdi
Chen, Qingyu
Xu, Kaidi
Hu, Xia
Chen, Tianlong
author_facet Liu, Zijie
Zhao, Xinyu
Peng, Jie
Zhu, Zhuangdi
Chen, Qingyu
Xu, Kaidi
Hu, Xia
Chen, Tianlong
contents Current medical AI systems often fail to replicate real-world clinical reasoning, as they are predominantly trained and evaluated on static text and question-answer tasks. These tuning methods and benchmarks overlook critical aspects like evidence-based reasoning and handling distracting information. To bridge this gap, we introduce a novel benchmark that simulates real-world diagnostic scenarios, integrating noise and difficulty levels aligned with USMLE standards. Moreover, we explore dialogue-based fine-tuning, which transforms static datasets into conversational formats to better capture iterative reasoning processes. Experiments show that dialogue-tuned models outperform traditional methods, with improvements of $9.64\%$ in multi-round reasoning scenarios and $6.18\%$ in accuracy in a noisy environment. Our findings highlight dialogue tuning as a promising approach for advancing clinically aligned and robust medical AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17860
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations
Liu, Zijie
Zhao, Xinyu
Peng, Jie
Zhu, Zhuangdi
Chen, Qingyu
Xu, Kaidi
Hu, Xia
Chen, Tianlong
Computation and Language
Artificial Intelligence
Current medical AI systems often fail to replicate real-world clinical reasoning, as they are predominantly trained and evaluated on static text and question-answer tasks. These tuning methods and benchmarks overlook critical aspects like evidence-based reasoning and handling distracting information. To bridge this gap, we introduce a novel benchmark that simulates real-world diagnostic scenarios, integrating noise and difficulty levels aligned with USMLE standards. Moreover, we explore dialogue-based fine-tuning, which transforms static datasets into conversational formats to better capture iterative reasoning processes. Experiments show that dialogue-tuned models outperform traditional methods, with improvements of $9.64\%$ in multi-round reasoning scenarios and $6.18\%$ in accuracy in a noisy environment. Our findings highlight dialogue tuning as a promising approach for advancing clinically aligned and robust medical AI systems.
title Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2501.17860