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://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.279/
- DOI:
- 10.18653/v1/2024.findings-acl.279
- 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)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.279.pdf