AI RESEARCH
Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers
arXiv CS.CL
•
ArXi:2606.02776v1 Announce Type: new 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 nstrated that this results in outcome disparities between sociographic groups, with some groups receiving advantageous outcomes than others.