arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.05396cs.CLcs.SE
收藏

FairCoder:通过编码任务探究高风险决策中语言模型的偏差

FairCoder: Probing LLM Bias in High-Stakes Decision Making via Coding Tasks

Pennsylvania State University(宾夕法尼亚州立大学);University of Southern California(南加州大学)

Yongkang Du, Jen-tse Huang, Jieyu Zhao, Lu Lin

AI总结:

研究通过FairCoder基准将决策制定设为编码任务,探究LLMs在多领域的偏差,针对现有指标不足提出FairScore指标,经实验揭示了此前未充分探索的偏差模式,凸显LLMs作决策代理的风险并提供评估框架。

摘要:

大语言模型(LLMs)越来越多地用于招聘和大学招生等高风险决策,其社会偏差备受关注。尽管LLMs被训练拒绝明确的偏见请求,但在规划和推理过程中可能会隐性泄露偏差。由于代码是LLMs内部逻辑编写的主要媒介,我们引入FairCoder基准,将决策制定框架为编码任务,以系统探究就业、教育和医疗领域的LLM偏差,涵盖多种公平性定义。鉴于现有指标在LLMs频繁拒绝请求时可能失效,我们提出FairScore指标,联合捕捉拒绝行为和群体层面结果多样性。对强大LLMs的1k样本数据集实验揭示了一致且此前未充分探索的偏差模式,如大学招生中优先考虑高收入家庭申请者。研究结果凸显了将LLMs用作决策代理的风险,并为未来研究提供了综合评估框架。

英文摘要:

Large language models (LLMs) are increasingly used in high-stakes decisions such as hiring and college admissions, making their social bias a critical concern. While LLMs are trained to refuse explicitly biased requests, bias can be leaked implicitly during LLM planning and reasoning process. As code becomes the primary medium for LLM internal logic-writing, we introduce FairCoder, a benchmark that frames decision-making as coding tasks to systematically probe LLM bias across employment, education, and healthcare domains, covering multiple fairness definitions. Considering that existing metrics may fail when LLMs frequently refuse the request, we propose FairScore, a metric that jointly captures refusal behavior and group-level outcome diversity. Experiments with a 1k-sample dataset on powerful LLMs reveal consistent and previously underexplored bias patterns, such as prioritizing applicants from high-income families in college admissions. Our findings highlight the risks of deploying LLMs as decision-making agents and provide a comprehensive evaluation framework for future research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑