UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?

Junda Wang, Zonghai Yao, Avijit Mitra, Samuel Osebe, Zhichao Yang, Hong Yu


Abstract
This paper presents UMASS_BioNLP team participation in the MEDIQA-Chat 2023 shared task for Task-A and Task-C. We focus especially on Task-C and propose a novel LLMs cooperation system named a doctor-patient loop to generate high-quality conversation data sets. The experiment results demonstrate that our approaches yield reasonable performance as evaluated by automatic metrics such as ROUGE, medical concept recall, BLEU, and Self-BLEU. Furthermore, we conducted a comparative analysis between our proposed method and ChatGPT and GPT-4. This analysis also investigates the potential of utilizing cooperation LLMs to generate high-quality datasets.
Anthology ID:
2023.clinicalnlp-1.49
Volume:
Proceedings of the 5th Clinical Natural Language Processing Workshop
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Anna Rumshisky
Venue:
ClinicalNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
460–471
Language:
URL:
https://aclanthology.org/2023.clinicalnlp-1.49
DOI:
10.18653/v1/2023.clinicalnlp-1.49
Bibkey:
Cite (ACL):
Junda Wang, Zonghai Yao, Avijit Mitra, Samuel Osebe, Zhichao Yang, and Hong Yu. 2023. UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 460–471, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations? (Wang et al., ClinicalNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.clinicalnlp-1.49.pdf