AI RESEARCH
Causal Stories from Sensor Traces: Auditing Epistemic Overreach in LLM-Generated Personal Sensing Explanations
arXiv CS.AI
•
ArXi:2605.08590v1 Announce Type: cross LLMs are increasingly used to explain personal sensing data, translating traces of activity and mood into natural-language accounts of why an anomalous day may have occurred. However, such explanations can sound coherent and personally meaningful even when the underlying evidence is sparse or missing. We