From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation 文章

ArXiv CS.AI2026-08-13PAPERen作者: Alireza S. Ziabari, Kat Ellis, Colleen Chan, Ding Tong
AI 安全
查看原文 →
关系图谱

From Prompting to Behavioral Alignment: Personalized LLM Judges for Recommendation Evaluation · 相关技术

相关技术

Large language modelDPOfine-tuningsequential behavioral alignment frameworkBaseline (zero-shot)bidirectional rationalization