真实性偏见及其超越：揭示大语言模型在问题求解推理中的隐藏信念
Veracity Bias and Beyond: Uncovering LLMs' Hidden Beliefs in Problem-Solving Reasoning
AI总结：
本研究通过实验揭示大语言模型在问题求解中表现出归因偏见和评估偏见，即对特定人口群体（如非裔美国人）的解决方案真实性判断存在系统性偏差，且该偏见深植于推理过程，影响其教育评估应用。
摘要：
尽管大语言模型（LLMs）在显式对齐中避免人口统计刻板印象，但研究表明它们在各种社会情境下仍会表现出偏见。在本工作中，我们发现LLMs在将解决方案的真实性与人口统计特征关联时表现出令人担忧的偏见。通过在数学、编程、常识和写作问题上对五个符合人类价值观的LLMs进行实验，我们揭示了这种真实性偏见的两种形式：归因偏见（Attribution Bias），即模型不成比例地将正确解决方案归因于某些人口统计群体；以及评估偏见（Evaluation Bias），即模型对相同解决方案的评估因感知到的作者人口统计特征而异。我们的结果显示普遍存在的偏见：LLMs在数学和编程问题中始终将更少的正确解决方案和更多的错误解决方案归因于非裔美国人群体，而亚裔作者身份在写作评估中最不受青睐。在附加研究中，我们展示了LLMs在可视化代码中自动为人口统计群体分配种族刻板印象颜色，表明这些偏见深深嵌入模型的推理过程中。我们的发现表明，人口统计偏见超越了表面刻板印象和社会情境挑衅，引发了对LLMs在教育和评估环境中部署的担忧。
英文摘要：
Despite LLMs' explicit alignment against demographic stereotypes, they have been shown to exhibit biases under various social contexts. In this work, we find that LLMs exhibit concerning biases in how they associate solution veracity with demographics. Through experiments across five human value-aligned LLMs on mathematics, coding, commonsense, and writing problems, we reveal two forms of such veracity biases: Attribution Bias, where models disproportionately attribute correct solutions to certain demographic groups, and Evaluation Bias, where models' assessment of identical solutions varies based on perceived demographic authorship. Our results show pervasive biases: LLMs consistently attribute fewer correct solutions and more incorrect ones to African-American groups in math and coding, while Asian authorships are least preferred in writing evaluation. In additional studies, we show LLMs automatically assign racially stereotypical colors to demographic groups in visualization code, suggesting these biases are deeply embedded in models' reasoning processes. Our findings indicate that demographic bias extends beyond surface-level stereotypes and social context provocations, raising concerns about LLMs' deployment in educational and evaluation settings.
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。
