conftrace_

activation engineering

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

topic consistency (1) concept engineering (1) response detoxification (1) large language model (1) model intervention (1) factual recall (1) temporal knowledge (1) dialogue system (1) steering vector (1) model alignment (1)

Papers

EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance ACL 2025 Temporal Alignment of Time Sensitive Facts with Activation Engineering EMNLP 2025 PaCE: Parsimonious Concept Engineering for Large Language Models NeurIPS 2024 Style Vectors for Steering Generative Large Language Models EACL 2024