小规模数据投毒是否会加剧大语言模型中与方言相关的偏见？
Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?
AI总结：
本研究通过小规模风格条件数据投毒，发现其能加剧大语言模型对方言输入的偏见，尤其是AAVE，并导致越狱行为，凸显了方言感知评估与风格-毒性解耦训练的必要性。
摘要：
风格条件数据投毒被识别为放大大型语言模型中社会语言学偏见的隐蔽载体。本研究使用小规模投毒预算，在指令微调期间将方言提示（主要是非裔美国英语（AAVE）和南方方言）与有毒或刻板印象的补全配对，探讨语言风格是否可作为有害行为的潜在触发器。在多个模型家族和规模中，投毒暴露提升了方言输入的毒性和刻板印象表达——对AAVE最为一致——而标准美式英语相对较低但并非免疫。结合基于分类器的毒性与LLM作为评判者的多指标审计揭示了即使在词汇毒性看似微弱时也存在刻板印象内容，表明传统检测器低估了社会语言学危害。此外，尽管投毒中缺乏明确辱骂词，投毒模型表现出新兴的越狱行为，暗示对齐弱化而非记忆。这些发现强调了需要方言感知评估、内容级刻板印象审计以及明确将风格与毒性解耦的训练协议，以防止通过看似微小的、基于风格的污染加剧偏见。
英文摘要：
Style-conditioned data poisoning is identified as a covert vector for amplifying sociolinguistic bias in large language models. Using small poisoned budgets that pair dialectal prompts -- principally African American Vernacular English (AAVE) and a Southern dialect -- with toxic or stereotyped completions during instruction tuning, this work probes whether linguistic style can act as a latent trigger for harmful behavior. Across multiple model families and scales, poisoned exposure elevates toxicity and stereotype expression for dialectal inputs -- most consistently for AAVE -- while Standard American English remains comparatively lower yet not immune. A multi-metric audit combining classifier-based toxicity with an LLM-as-a-judge reveals stereotype-laden content even when lexical toxicity appears muted, indicating that conventional detectors under-estimate sociolinguistic harms. Additionally, poisoned models exhibit emergent jailbreaking despite the absence of explicit slurs in the poison, suggesting weakened alignment rather than memorization. These findings underscore the need for dialect-aware evaluation, content-level stereotype auditing, and training protocols that explicitly decouple style from toxicity to prevent bias amplification through seemingly minor, style-based contamination.
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。
