conftrace_

activation editing

6 papers

Explore in graph

Co-occurring keywords

large language model (13587) model editing (159) steering vector (33) mechanistic interpretability (133) model alignment (226) spectral projection (3) representation steering (9) neuron analysis (32) internal activation (7) toxicity reduction (27)

Papers

Query-Routed Activation Editing with Truth-hierarchical Preference Optimization AAAI 2026
Token-Aware Editing of Internal Activations for Large Language Model Alignment EMNLP 2025
How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis EMNLP 2025
Sparse Activation Editing for Reliable Instruction Following in Narratives EMNLP 2025
Spectral Editing of Activations for Large Language Model Alignment NIPS 2024
Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective EMNLP 2024