2 papers
cs.CL2025
HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
Xin Tong, Zhi Lin, Jingya Wang +1
Large Language Models (LLMs) often produce hallucinations in retrieval-augmented or long-context generation, even when relevant evidence is present. This stems from two issues: hea…
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…