conftrace_

activation intervention

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (5) model steering (2) visual counterfactual (1) reasoning performance (1) language model truthfulness (1) personality alignment (1) layerwise additive (1) model truthfulness (1) parameter dynamics (1) control vector (1)

Papers

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics ACL 2026 Improving Reasoning Performance in Large Language Models via Representation Engineering ICLR 2025 Multilingual Political Views of Large Language Models: Identification and Steering IJCNLP 2025 Personality Alignment of Large Language Models ICLR 2025 Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts EMNLP 2025 Probe-Free Low-Rank Activation Intervention NAACL 2025 Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors ICLR 2025 Task-driven Layerwise Additive Activation Intervention NAACL 2025