LLM Sensitivity Evaluation Framework for Clinical Diagnosis

Chenwei Yan, Xiangling Fu, Yuxuan Xiong, Tianyi Wang, Siu Cheung Hui, Ji Wu, Xien Liu


Abstract
Large language models (LLMs) have demonstrated impressive performance across various domains. However, for clinical diagnosis, higher expectations are required for LLM’s reliability and sensitivity: thinking like physicians and remaining sensitive to key medical information that affects diagnostic reasoning, as subtle variations can lead to different diagnosis results. Yet, existing works focus mainly on investigating the sensitivity of LLMs to irrelevant context and overlook the importance of key information. In this paper, we investigate the sensitivity of LLMs, i.e. GPT-3.5, GPT-4, Gemini, Claude3 and LLaMA2-7b, to key medical information by introducing different perturbation strategies. The evaluation results highlight the limitations of current LLMs in remaining sensitive to key medical information for diagnostic decision-making. The evolution of LLMs must focus on improving their reliability, enhancing their ability to be sensitive to key information, and effectively utilizing this information. These improvements will enhance human trust in LLMs and facilitate their practical application in real-world scenarios. Our code and dataset are available at https://github.com/chenwei23333/DiagnosisQA.
Anthology ID:
2025.coling-main.207
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3083–3094
Language:
URL:
https://aclanthology.org/2025.coling-main.207/
DOI:
Bibkey:
Cite (ACL):
Chenwei Yan, Xiangling Fu, Yuxuan Xiong, Tianyi Wang, Siu Cheung Hui, Ji Wu, and Xien Liu. 2025. LLM Sensitivity Evaluation Framework for Clinical Diagnosis. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3083–3094, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
LLM Sensitivity Evaluation Framework for Clinical Diagnosis (Yan et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.207.pdf