SubmissionNumber#=%=#30
FinalPaperTitle#=%=#Gender-Neutral Large Language Models for Medical Applications: Reducing Bias in PubMed Abstracts
ShortPaperTitle#=%=#
NumberOfPages#=%=#10
CopyrightSigned#=%=#Elizabeth Schaefer
JobTitle#==#
Organization#==#Yale University, Department of Computer Science, 51 Prospect St, New Haven, CT 06511
Abstract#==#This paper presents a pipeline for mitigating gender bias in large language models (LLMs) used in medical literature by neutralizing gendered occupational pronouns. A set of 379,000 PubMed abstracts from 1965-1980 was processed to identify and modify pronouns tied to professions. We developed a BERT-based model, "Modern Occupational Bias Elimination with Refined Training," or "MOBERT," trained on these neutralized abstracts, and compared it with "1965BERT," trained on the original dataset. MOBERT achieved a 70% inclusive replacement rate, while 1965BERT reached only 4%. A further analysis of MOBERT revealed that pronoun replacement accuracy correlated with the frequency of occupational terms in the training data. We propose expanding the dataset and refining the pipeline to improve performance and ensure more equitable language modeling in medical applications.
Author{1}{Firstname}#=%=#Elizabeth
Author{1}{Lastname}#=%=#Schaefer
Author{1}{Username}#=%=#eschaefer17
Author{1}{Email}#=%=#schaefer.elizabeth@gmail.com
Author{1}{Affiliation}#=%=#Yale University
Author{2}{Firstname}#=%=#Kirk
Author{2}{Lastname}#=%=#Roberts
Author{2}{Username}#=%=#captkrob
Author{2}{Email}#=%=#kirkroberts@gmail.com
Author{2}{Affiliation}#=%=#University of Texas Health Science Center at Houston

==========
èéáğö