Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is a complex challenge, and approaches that do so typically utilize standard question-answer (QA) styled schemes. Such methods often overlook deeper issues by interpreting the model's refusal responses as positive fairness measurements, which creates a false sense of fairness. In this work, we introduce the concept of silenced biases, which are unfair preferences encoded within models' latent space and are effectively concealed by safety-alignment. Previous approaches that considered similar indirect biases often relied on prompt manipulation or handcrafted implicit queries, which present limited scalability and risk contaminating the evaluation process with additional biases. We propose the Silenced Bias Benchmark (SBB), which aims to uncover these biases by employing activation steering to reduce model refusals during QA. SBB supports easy expansion to new demographic groups and subjects, presenting a fairness evaluation framework that encourages the future development of fair models and tools beyond the masking effects of alignment training. We demonstrate our approach over multiple LLMs, where our findings expose an alarming distinction between models' direct responses and their underlying fairness issues.

翻译：安全对齐的大型语言模型（LLMs）正日益普及，尤其在公平性至关重要且偏见输出可能造成重大危害的敏感应用中。然而，评估模型的公平性是一项复杂挑战，现有方法通常采用标准问答（QA）式方案，往往通过将模型的拒绝响应解读为积极公平性度量来掩盖深层问题，从而制造虚假的公平感。本文提出"被沉默的偏见"概念，指代编码在模型潜在空间中、被安全对齐有效隐藏的不公平偏好。先前考虑类似间接偏见的方法多依赖提示操控或手工设计的隐式查询，这不仅扩展性有限，还存在向评估过程引入额外偏见的风险。我们提出被沉默的偏见基准（SBB），通过应用激活引导减少QA过程中模型的拒绝响应，旨在揭示这些潜在偏见。SBB支持轻松扩展至新人口群体和主题，构建了一个超越对齐训练掩蔽效应的公平性评估框架，鼓励开发更公平的模型与工具。我们在多个LLM上验证该方法，研究结果揭示了模型直接响应与其潜在公平性问题之间令人警醒的差异。