arXiv cs.AI by Synapse Flow 編集部

DeEscalWild: A Real-World Benchmark for Automated De-Escalation Training with SLMs

概要

arXiv:2604.13075v2 Announce Type: replace-cross Abstract: Effective de-escalation is critical for law enforcement safety and community trust, yet traditional training methods lack scalability and realism. While Large Language Models (LLMs) enable dynamic, open-ended simulations, their substantial c…

元記事を読む →

関連記事