Two-Pronged Human Evaluation of ChatGPT Self-Correction in Radiology Report Simplification

Ziyu Yang, Santhosh Cherian, Slobodan Vucetic


Abstract
Radiology reports are highly technical documents aimed primarily at doctor-doctor communication. There has been an increasing interest in sharing those reports with patients, necessitating providing them patient-friendly simplifications of the original reports. This study explores the suitability of large language models in automatically generating those simplifications. We examine the usefulness of chain-of-thought and self-correction prompting mechanisms in this domain. We also propose a new evaluation protocol that employs radiologists and laypeople, where radiologists verify the factual correctness of simplifications, and laypeople assess simplicity and comprehension. Our experimental results demonstrate the effectiveness of self-correction prompting in producing high-quality simplifications. Our findings illuminate the preferences of radiologists and laypeople regarding text simplification, informing future research on this topic.
Anthology ID:
2024.findings-acl.279
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4701–4714
Language:
URL:
https://aclanthology.org/2024.findings-acl.279
DOI:
10.18653/v1/2024.findings-acl.279
Bibkey:
Cite (ACL):
Ziyu Yang, Santhosh Cherian, and Slobodan Vucetic. 2024. Two-Pronged Human Evaluation of ChatGPT Self-Correction in Radiology Report Simplification. In Findings of the Association for Computational Linguistics: ACL 2024, pages 4701–4714, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Two-Pronged Human Evaluation of ChatGPT Self-Correction in Radiology Report Simplification (Yang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.279.pdf