Appraising the Potential Uses and Harms of Large Language Models for Medical Systematic Reviews

Hye Sun Yun, Thomas A. Trikalinos, Iain J. Marshall, Byron C. Wallace

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

4 Citations (Scopus)

Abstract

Medical systematic reviews play a vital role in healthcare decision making and policy. However, their production is time-consuming, limiting the availability of high-quality and up-to-date evidence summaries. Recent advances in large language models (LLMs) offer the potential to automatically generate literature reviews on demand, addressing this issue. However, LLMs sometimes generate inaccurate (and potentially misleading) texts by “hallucination” or omission. In healthcare, this can make LLMs unusable at best and dangerous at worst. We conducted 16 interviews with international systematic review experts to characterize the perceived utility and risks of LLMs in the specific context of medical evidence reviews. Experts indicated that LLMs can assist in the writing process by drafting summaries, generating templates, distilling information, and crosschecking information. But they also raised concerns regarding confidently composed but inaccurate LLM outputs and other potential downstream harms, including decreased accountability and proliferation of low-quality reviews. Informed by this qualitative analysis, we identify criteria for rigorous evaluation of biomedical LLMs aligned with domain expert views.

Original languageEnglish
Title of host publicationEMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings
EditorsHouda Bouamor, Juan Pino, Kalika Bali
PublisherAssociation for Computational Linguistics (ACL)
Pages10122-10139
Number of pages18
ISBN (Electronic)9798891760608
Publication statusPublished - 2023
Event2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023 - Hybrid, Singapore, Singapore
Duration: 6 Dec 202310 Dec 2023

Publication series

NameEMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023
Country/TerritorySingapore
CityHybrid, Singapore
Period6/12/202310/12/2023

Fingerprint

Dive into the research topics of 'Appraising the Potential Uses and Harms of Large Language Models for Medical Systematic Reviews'. Together they form a unique fingerprint.

Cite this