基于模板的探测器在评估大语言模型中的反事实偏见时是不完美的透镜
Template-Based Probes Are Imperfect Lenses for Counterfactual Bias Evaluation in LLMs
AI总结：
本研究发现基于模板的探测器在评估大语言模型中的反事实偏见时存在系统性扭曲，需更严谨的方法以区分真实偏见与语言惯例影响。
摘要：
大语言模型（LLMs）中的偏见有多种形式，从显性的歧视到隐含的刻板印象。反事实偏见评估是一种广泛用于量化偏见的方法，通常依赖于基于模板的探测器，这些探测器明确指定了群体成员身份。其目的是衡量LLM执行任务时的结果是否对群体成员身份的变化保持不变。在本工作中，我们发现基于模板的探测器可能在偏见测量中引入系统性扭曲。具体来说，我们一致发现，此类探测器表明LLM将与白人种族相关的文本以不成比例的高频率分类为负面。这种现象在大量LLM、多种不同的基于模板的探测器以及不同的分类方法中都一致观察到。我们推测，这种现象可能是由于预训练数据中存在语言不对称性，以标记性（例如，黑人总统 vs. 总统）和用于偏见测量的模板（例如，黑人总统 vs. 白人总统）的形式人为产生的。这些发现强调了在反事实偏见评估中需要更严格的方法，以确保观察到的差异反映真实的偏见，而不是语言惯例的产物。
英文摘要：
Bias in large language models (LLMs) has many forms, from overt discrimination to implicit stereotypes. Counterfactual bias evaluation is a widely used approach to quantifying bias and often relies on template-based probes that explicitly state group membership. It aims to measure whether the outcome of a task performed by an LLM is invariant to a change in group membership. In this work, we find that template-based probes can introduce systematic distortions in bias measurements. Specifically, we consistently find that such probes suggest that LLMs classify text associated with White race as negative at disproportionately elevated rates. This is observed consistently across a large collection of LLMs, over several diverse template-based probes, and with different classification approaches. We hypothesize that this arises artificially due to linguistic asymmetries present in LLM pretraining data, in the form of markedness, (e.g., Black president vs. president) and templates used for bias measurement (e.g., Black president vs. White president). These findings highlight the need for more rigorous methodologies in counterfactual bias evaluation, ensuring that observed disparities reflect genuine biases rather than artifacts of linguistic conventions.
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。
