话题作为社会人口统计的代理：对话上下文如何影响大语言模型的回答
Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers
AI总结：
研究大语言模型在高风险场景中对话上下文对回答差异的影响，发现话题是社会人口统计差异的主要驱动因素，且影响方式不可预测。
摘要：
当大语言模型（LLM）用于高风险场景（如法律、医疗和金融建议）时，即使单次对话历史也足以导致用户间结果差异。先前研究表明，这会导致社会人口统计群体之间的结果差异，某些群体获得比其他群体更有利的结果。在这项工作中，我们证明LLM实际上难以从单次对话历史推断用户的社会人口统计信息，并且尽管社会人口统计群体之间存在差异，但差异幅度很小。为了探究这些差异的主要驱动因素，我们将用户社会人口统计信息与对话的一系列（心理）语言学特征（包括对话话题、情感和可读性）进行比较。我们发现，在对话上下文中，对话话题最能预测LLM生成的建议，这些话题在一定程度上充当社会人口统计群体的代理，并且常常以不可预测的方式影响建议。这令人担忧，并强调未来研究需要更好地理解，并在必要时减轻高风险场景中对话上下文对LLM输出的影响。
英文摘要：
When large language models (LLMs) are used in high-stakes scenarios, such as legal, medical and financial advice, even a single conversation history is enough to drive differences in outcomes between users. Prior work has demonstrated that this results in outcome disparities between sociodemographic groups, with some groups receiving more advantageous outcomes than others. In this work, we demonstrate that LLMs actually struggle to infer user sociodemographics from a single conversation history and that although there are disparities between sociodemographic groups, they are minimal in magnitude. To investigate what is the main driver of disparities between users, we compare user sociodemographics to a range of (psycho)linguistic features of conversations, including conversation topic, emotions, and readability. We find that conversation topics are most predictive of LLM-generated advice within a conversational context, which, to some extent, function as proxies for sociodemographic groups and often affect advice in unpredictable ways. This is cause for concern and highlights the need for future research to better understand the effect of conversational context on LLM outputs in high-stakes scenarios.
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。
