AI RESEARCH
Food Noise & False Safety: A Systematic Evaluation of How LLMs Fail to Adapt to Eating Disorder Queries with Clinician Feedback
arXiv CS.AI
•
ArXi:2606.02444v1 Announce Type: new Recent evidence shows that people with eating disorders (EDs) are increasingly seeking guidance, advice, and emotional from Large Language Model (LLM)-based chat systems. Although these systems are not designed to provide clinical advice, their perceived expertise, neutrality and accessibility make them a frequent, albeit risky, source of.