conftrace_

neuron selection

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) safety-utility conflict (1) parameter isolation (1) concept neuron selection (1) neuron identification (1) internal representation (1) open-domain question answering (1) linear probing (1) hallucination detection (1) parameter-efficient tuning (1)

Papers

Continual Personalization for Diffusion Models ICCV 2025 Detecting Hallucination in Large Language Models Through Deep Internal Representation Analysis IJCAI 2025 LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint ACL 2025