GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models
Oct 14, 2024·,,,
,,,,,·
1 min read
Kunsheng Tang
Wenbo Zhou
Jie Zhang
Aishan Liu
Gelei Deng
Shuai Li
Peigui Qi
Weiming Zhang
Tianwei Zhang
Nenghai Yu
Abstract
GenderCARE is a framework for assessing and reducing gender bias in large language models. It defines evaluation criteria, introduces the GenderPair benchmark, and applies debiasing techniques based on counterfactual data augmentation and fine-tuning.
Type
Publication
Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS)
GenderCARE contributes practical criteria, benchmarks, and reduction techniques for measuring and mitigating gender bias in LLMs while preserving general task performance.
