谁在提问？从残障框架查询视角研究大语言模型中的偏见
Who's Asking? Investigating Bias Through the Lens of Disability Framed Queries in LLMs
AI总结：
该研究首次系统性审计8款不同规模指令微调LLM的残障相关人口统计偏见，发现模型易无依据推断人口属性、残障语境会放大偏见且大模型偏见更显著，提出用弃权校准和反事实微调缓解该问题。
摘要：
大语言模型（LLM）通常仅从措辞就能推断用户的人口统计特征，即便没有提供明确的人口统计信息，这也可能导致带有偏见的回复。残障线索在塑造这类推断过程中所起的作用，目前在很大程度上仍属未知。因此，我们针对8个参数规模从3B到72B的最先进指令微调LLM，开展了首次以残障为条件的人口统计偏见系统性审计。我们使用一个平衡模板语料库，将9个残障类别与6个现实商业领域配对，在中性条件和残障感知条件下，提示每个模型预测5项人口统计属性——性别、社会经济地位、教育程度、文化背景和居住地。\n在各类提示中，模型在高达97%的案例中给出了明确的人口统计猜测，暴露出强烈的无明确依据就做出任意推断的倾向。残障语境会大幅改变预测的属性分布，而领域语境会进一步放大这些偏差。我们观察到，规模更大的模型对残障线索更敏感，同时也更容易产生偏见推理，这表明仅靠模型规模扩大并不能缓解刻板印象放大的问题。\n我们的发现揭示了残障歧视与其他人口统计刻板印象之间持续存在的交叉性，指出了当前对齐策略中存在的关键盲点。我们发布了评估框架和结果，以推动具备残障包容性的基准测试建设，并建议整合弃权（不执行）校准和反事实微调，以抑制无根据的人口统计推断。代码和数据将在论文录用后发布。
英文摘要：
Large Language Models (LLMs) routinely infer users demographic traits from phrasing alone, which can result in biased responses, even when no explicit demographic information is provided. The role of disability cues in shaping these inferences remains largely uncharted. Thus, we present the first systematic audit of disability-conditioned demographic bias across eight state-of-the-art instruction-tuned LLMs ranging from 3B to 72B parameters. Using a balanced template corpus that pairs nine disability categories with six real-world business domains, we prompt each model to predict five demographic attributes - gender, socioeconomic status, education, cultural background, and locality - under both neutral and disability-aware conditions. Across a varied set of prompts, models deliver a definitive demographic guess in up to 97\% of cases, exposing a strong tendency to make arbitrary inferences with no clear justification. Disability context heavily shifts predicted attribute distributions, and domain context can further amplify these deviations. We observe that larger models are simultaneously more sensitive to disability cues and more prone to biased reasoning, indicating that scale alone does not mitigate stereotype amplification. Our findings reveal persistent intersections between ableism and other demographic stereotypes, pinpointing critical blind spots in current alignment strategies. We release our evaluation framework and results to encourage disability-inclusive benchmarking and recommend integrating abstention calibration and counterfactual fine-tuning to curb unwarranted demographic inference. Code and data will be released on acceptance.
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。
