Persona-basierte Mehrdialog-Sicherheitsevaluation mit 1.674 DialogpaarenLaw & ethics

Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversations

Prerna Juneja, Lika LomidzeProceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)July 1, 2026

Original publication

Dialogatlas verifies this real publication bibliographically and links directly to the original source. This record does not contain an automatically generated summary.

Open the article at the original source

Source and record