用中性化职业代词减少医学大模型偏见，提升性别包容性。
Gender-Neutral Large Language Models for Medical Applications: Reducing Bias in PubMed Abstracts
- 通过中性化1965-1980年37.9万篇论文中的职业代词，构建无性别倾向数据集。
- 新模型MOBERT实现70%代词替换率，原模型仅4%。
- 模型表现与职业词频相关，适合医疗AI公平性研究者使用。
本文提出一种缓解医学领域大语言模型性别偏见的流程，通过中性化职业相关代词实现。基于1965至1980年间379,000篇PubMed摘要构建数据集，识别并修改与职业相关的性别化代词。我们开发了基于BERT的MOBERT模型，该模型在经中性化处理的数据上训练，并与在原始数据上训练的1965BERT进行对比。结果显示，MOBERT达到70%的包容性替换率，而1965BERT仅为4%。进一步分析表明，MOBERT的代词替换准确率与训练数据中职业术语的出现频率呈正相关。研究建议扩充数据集并优化流程，以提升模型性能，推动医疗应用中更公平的语言建模。
原文摘要 · Abstract (English)
This paper presents a pipeline for mitigating gender bias in large language models (LLMs) used in medical literature by neutralizing gendered occupational pronouns. A dataset 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 its performance 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。