自带提示词:面向LLM的用例特定偏见和公平性评估
Bring Your Own Prompts: Use-Case-Specific Bias and Fairness Evaluation for LLMs
AI总结:
本文提出一种决策框架,通过映射LLM用例到相关偏见和公平性指标,考虑任务类型、提示中是否包含受保护属性提及及利益相关者优先级,引入新型指标并开源库langfair进行实践验证。
摘要:
大型语言模型(LLM)中的偏见和公平性风险在部署上下文中差异显著,现有方法缺乏系统指导以选择合适评估指标。本文提出一个决策框架,根据任务类型、提示中是否包含受保护属性提及以及利益相关者优先级,将LLM用例(由模型和提示群体特征化)映射到相关的偏见和公平性指标。该框架处理毒性、刻板印象、反事实不公平和分配性伤害,并引入基于刻板印象分类器和文本相似度的反事实调整指标。我们开源了Python库langfair用于实际应用。对五个LLM和五个提示群体的用例进行的广泛实验表明,公平性风险不能仅凭基准性能可靠评估:一个提示数据集的结果可能高估或低估另一个数据集的风险,强调公平性评估必须基于具体的部署上下文。
英文摘要:
Bias and fairness risks in Large Language Models (LLMs) vary substantially across deployment contexts, yet existing approaches lack systematic guidance for selecting appropriate evaluation metrics. We present a decision framework that maps LLM use cases, characterized by a model and population of prompts, to relevant bias and fairness metrics based on task type, whether prompts contain protected attribute mentions, and stakeholder priorities. Our framework addresses toxicity, stereotyping, counterfactual unfairness, and allocational harms, and introduces novel metrics based on stereotype classifiers and counterfactual adaptations of text similarity measures. We release an open-source Python library, \texttt{langfair}, for practical adoption. Extensive experiments on use cases across five LLMs and five prompt populations demonstrate that fairness risks cannot be reliably assessed from benchmark performance alone: results on one prompt dataset likely overstate or understate risks for another, underscoring that fairness evaluation must be grounded in the specific deployment context.
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。