Skip to content
conftrace_

activation editing

9 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) model editing (3) llm alignment (2) steering vector (2) mechanistic interpretability (2) model alignment (2) spectral projection (1) representation steering (1) membership inference attack (1) neuron analysis (1)

Papers

Query-Routed Activation Editing with Truth-hierarchical Preference Optimization AAAI 2026 Differentially Private Steering for Large Language Model Alignment ICLR 2025 How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis EMNLP 2025 Joint Localization and Activation Editing for Low-Resource Fine-Tuning ICML 2025 Sparse Activation Editing for Reliable Instruction Following in Narratives EMNLP 2025 Steering Protein Language Models ICML 2025 Token-Aware Editing of Internal Activations for Large Language Model Alignment EMNLP 2025 Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective EMNLP 2024 Spectral Editing of Activations for Large Language Model Alignment NeurIPS 2024