Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors
Xin Tong, Zhi Lin, Jingya Wang +2
Large language models (LLMs) enforce safety alignment to reliably refuse malicious requests, yet the same blanket safeguards also block legitimate uses in policing, defense, and ot…
cs.LG2025
Spectral Logit Sculpting: Adaptive Low-Rank Logit Transformation for Controlled Text Generation
Jin Li, Zhebo Wang, Tianliang Lu +3
Entropy-based inference methods have gained traction for improving the reliability of Large Language Models (LLMs). However, many existing approaches, such as entropy minimization…