3 artifacts matching
15 Jul 2026 Proceedings of the IASEAI Conference (published by AAAI) Peer-reviewed
Peer-reviewed
Independent Clinical Evaluation of General-Purpose LLM Responses to Signals of Suicide Risk
Conference paper from UL Research Institutes' Digital Safety group and Sentio University assessing whether a general-purpose open-weight model follows clinically derived guidelines for ethical commun…
15 Jul 2026 Proceedings of the IASEAI Conference (published by AAAI) Peer-reviewed
Peer-reviewed
Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis
Conference paper from Apart Research with co-authors at the London School of Economics and the Stanford Institute for Human-Centered AI, testing whether automated judges can stand in for human raters…
15 Jul 2026 Proceedings of the IASEAI Conference (published by AAAI) Peer-reviewed
Peer-reviewed
Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users
Exploratory study from Saarland University and Durham University arguing that safety evaluation of assistant advice cannot be done without the user's context. Advice prompts on health and personal fi…