CoBia:构造的对话能触发 LLMs 中原本隐蔽的社会偏见
CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs
AI总结:
本文提出轻量级对抗攻击套件 CoBia,通过构造包含偏见声明的对话评估 11 个 LLMs 在六个社会人口类别上的偏见表现,发现刻意构造的对话能可靠揭示模型深层偏见放大现象且模型常无法拒绝偏见后续问题。
摘要:
模型构建方面的改进(包括强化的安全护栏)使得大型语言模型(LLMs)越来越能通过标准安全检查。然而,LLMs 在对话中有时会暴露出有害行为,例如表达种族主义观点。为了系统地分析这一现象,我们引入了 CoBia,这是一套轻量级对抗攻击方法,使我们能够细化 LLMs 在对话中偏离规范或伦理行为的条件范围。CoBia 会构造一段对话,让模型针对某个社会群体发表带有偏见的声明。然后,我们评估模型是否能从捏造的偏见声明中恢复,并拒绝带有偏见的后续问题。我们评估了 11 个开源及专有 LLMs,涉及与个人安全和公平待遇相关的六个社会人口类别,即性别、种族、宗教、国籍、性取向及其他。我们的评估基于既有的基于 LLM 的偏见指标,并将结果与人类判断进行比较,以界定 LLMs 的可靠性和对齐程度。结果表明,刻意构造的对话能可靠地揭示偏见放大现象,且 LLMs 在对话中常常无法拒绝带有偏见的后续问题。这种形式的压力测试突显了通过交互可以暴露出深层嵌入的偏见。代码和相关工件可在 https://github.com/nafisenik/CoBia 获取。
英文摘要:
Improvements in model construction, including fortified safety guardrails, allow Large language models (LLMs) to increasingly pass standard safety checks. However, LLMs sometimes slip into revealing harmful behavior, such as expressing racist viewpoints, during conversations. To analyze this systematically, we introduce CoBia, a suite of lightweight adversarial attacks that allow us to refine the scope of conditions under which LLMs depart from normative or ethical behavior in conversations. CoBia creates a constructed conversation where the model utters a biased claim about a social group. We then evaluate whether the model can recover from the fabricated bias claim and reject biased follow-up questions. We evaluate 11 open-source as well as proprietary LLMs for their outputs related to six socio-demographic categories that are relevant to individual safety and fair treatment, i.e., gender, race, religion, nationality, sex orientation, and others. Our evaluation is based on established LLM-based bias metrics, and we compare the results against human judgments to scope out the LLMs' reliability and alignment. The results suggest that purposefully constructed conversations reliably reveal bias amplification and that LLMs often fail to reject biased follow-up questions during dialogue. This form of stress-testing highlights deeply embedded biases that can be surfaced through interaction. Code and artifacts are available at https://github.com/nafisenik/CoBia.
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。