conftrace_

activation steering

60 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (21) vision-language model (8) safety alignment (8) model interpretability (5) syllogistic reasoning (4) jailbreak defense (4) jailbreak attack (4) attention head (4) language model (4) ai safety (4)

Papers

Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2 EMNLP 2025 Steering Protein Language Models ICML 2025 SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models EMNLP 2025 Understanding How CodeLLMs (Mis)Predict Types with Activation Steering EMNLP 2025 Multi-property Steering of Large Language Models with Dynamic Activation Composition EMNLP 2024 Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization NeurIPS 2024 Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations EMNLP 2024 Steering Llama 2 via Contrastive Activation Addition ACL 2024 Who's asking? User personas and the mechanics of latent misalignment NeurIPS 2024 Inference-Time Intervention: Eliciting Truthful Answers from a Language Model NeurIPS 2023