Measuring and mitigating overreliance to build human-compatible AI

ArXi:2509.08010v2 Announce Type: replace-cross Large language models (LLMs) distinguish themselves from previous technologies by functioning as collaborative ``thought partners,'' capable of engaging fluidly in natural language on a range of tasks. As LLMs increasingly influence consequential decisions across diverse domains from healthcare to personal advice, the risk of overreliance -- relying on LLMs beyond their capabilities -- grows. This paper argues that measuring and mitigating overreliance must become central to LLM research and deployment.