FAMESUMM

Investigating and Improving Faithfulness of Medical Summarization

authored by

Nan Zhang, Yusen Zhang, Wu Guo, Prasenjit Mitra, Rui Zhang

Abstract

Summaries of medical text shall be faithful by being consistent and factual with source inputs, which is an important but understudied topic for safety and efficiency in healthcare. In this paper, we investigate and improve faithfulness in summarization on a broad range of medical summarization tasks. Our investigation reveals that current summarization models often produce unfaithful outputs for medical input text. We then introduce FAMESUMM, a framework to improve faithfulness by fine-tuning pre-trained language models based on medical knowledge. FAMESUMM performs contrastive learning on designed sets of faithful and unfaithful summaries, and it incorporates medical terms and their contexts to encourage faithful generation of medical terms. We conduct comprehensive experiments on three datasets in two languages: health question and radiology report summarization datasets in English, and a patient-doctor dialogue dataset in Chinese. Results demonstrate that FAMESUMM is flexible and effective by delivering consistent improvements over mainstream language models such as BART, T5, mT5, and PEGASUS, yielding state-of-the-art performances on metrics for faithfulness and general quality. Human evaluation by doctors also shows that FAMESUMM generates more faithful outputs. Our code is available at github.com/psunlpgroup/FaMeSumm.

Organisation(s)

L3S Research Centre

External Organisation(s)

Pennsylvania State University
Zhengzhou University

Type

Conference contribution

Pages

10915-10931

No. of pages

Publication date

2023

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

Computational Theory and Mathematics, Computer Science Applications, Information Systems, Linguistics and Language

Sustainable Development Goals

SDG 3 - Good Health and Well-being

Electronic version(s)

https://doi.org/10.18653/v1/2023.emnlp-main.673 (Access: Open)