使用共指消解中的置信度差异研究大型语言模型中的交叉偏见
Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution
AI总结：
本研究扩展单轴公平性评估，通过构建WinoIdentity基准和提出共指置信度差异指标，评估LLMs在交叉身份下的偏见，发现模型在反刻板印象环境中对双重劣势身份置信度差异高达40%，且表明其高性能源于记忆而非推理。
摘要：
大型语言模型（LLMs）取得了令人瞩目的性能，这导致它们被广泛采用为招聘和录取等资源受限环境中的决策支持工具。然而，科学界已有共识，AI系统会反映并加剧社会偏见，引发了在关键社会环境中使用时基于身份的伤害的担忧。先前的工作通过评估不同语言推理任务中的人口统计学差异，为评估LLMs中的偏见奠定了坚实的基础。在本研究中，我们将单轴公平性评估扩展到交叉偏见，认识到当多个歧视轴交叉时，它们会产生截然不同的劣势模式。我们通过在WinoBias数据集中增加跨越10个属性（包括年龄、国籍和种族）的25个人口统计标记，并与二元性别交叉，创建了一个名为WinoIdentity的新基准，生成了245,700个提示来评估50种不同的偏见模式。聚焦于因代表性不足而导致的遗漏伤害，我们从不确定性的视角研究偏见，并提出了一种称为共指置信度差异的群体（非）公平性指标，该指标衡量模型对某些交叉身份的置信度是否高于或低于其他身份。我们评估了五个最近发布的LLMs，发现在体型、性取向和社会经济地位等各种人口统计属性上，置信度差异高达40%，模型在反刻板印象环境中对双重劣势身份最为不确定。令人惊讶的是，即使是霸权或特权标记的共指置信度也会下降，这表明LLMs近期令人瞩目的性能更可能归因于记忆而非逻辑推理。值得注意的是，这是价值对齐和有效性方面的两个独立失败，它们可能叠加从而造成社会伤害。
英文摘要：
Large language models (LLMs) have achieved impressive performance, leading to their widespread adoption as decision-support tools in resource-constrained contexts like hiring and admissions. There is, however, scientific consensus that AI systems can reflect and exacerbate societal biases, raising concerns about identity-based harm when used in critical social contexts. Prior work has laid a solid foundation for assessing bias in LLMs by evaluating demographic disparities in different language reasoning tasks. In this work, we extend single-axis fairness evaluations to examine intersectional bias, recognizing that when multiple axes of discrimination intersect, they create distinct patterns of disadvantage. We create a new benchmark called WinoIdentity by augmenting the WinoBias dataset with 25 demographic markers across 10 attributes, including age, nationality, and race, intersected with binary gender, yielding 245,700 prompts to evaluate 50 distinct bias patterns. Focusing on harms of omission due to underrepresentation, we investigate bias through the lens of uncertainty and propose a group (un)fairness metric called Coreference Confidence Disparity which measures whether models are more or less confident for some intersectional identities than others. We evaluate five recently published LLMs and find confidence disparities as high as 40% along various demographic attributes including body type, sexual orientation and socio-economic status, with models being most uncertain about doubly-disadvantaged identities in anti-stereotypical settings. Surprisingly, coreference confidence decreases even for hegemonic or privileged markers, indicating that the recent impressive performance of LLMs is more likely due to memorization than logical reasoning. Notably, these are two independent failures in value alignment and validity that can compound to cause social harm.
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。
