2 papers
cs.LG2026
Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
Wang Cai, Yilin Wen, Jinchang Hou +5
Safety alignment in Large Language Models (LLMs) inherently presents a multi-objective optimization conflict, often accompanied by an unintended degradation of general capabilities…
cs.CL2025
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
Xingyu Lin, Yilin Wen, En Wang +4
Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly by boosting their mathematical performance.…