作者位次 #3/13ACL 2026Poster· Natural Language Processing
Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety
Can Jin · Rui Wu · Tong Che · Qixin ZHANG · Hongwu Peng · Jiahui Zhao · Zhenting Wang · Wenqi Wei · Ligong Han · Zhao Zhang · Yuan Cao · Ruixiang Tang · Dimitris N. Metaxas
摘要
Ensuring that Large Language Models (LLMs) adhere to safety principles without refusing benign requests remains a significant challenge. While OpenAI introduces deliberative alignment (DA) to enhance the safety of its o-series models through reasoning over detailed “code-like” safety rules, the e...