Reward-free Alignment for Conflicting Objectives 文章

ArXiv CS.CL2026-05-26NEWSen作者: Peter Chen, Xiaopeng Li, Xi Chen, Tianyi Lin

查看原文 →

Reward-free Alignment for Conflicting Objectives · 相关技术

相关技术

ODE PLA LLM language model alignment Verse Referring expression comprehension (REC)Parts-of-Speech (POS) tags PPR LMM large language models IMU ICT HIS For FOL DiT CLI AnE ARG ANN Table