conftrace_

concept vector

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) model steering (2) representation engineering (2) language model (2) dehumanization analysis (1) lgbtq+ individual (1) sexual interaction (1) harmful stereotype (1) relative pose estimation (1) llm auditing (1)

Papers

ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors CVPR 2026 Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering EACL 2026 Fine-Grained Interpretation of Political Opinions in Large Language Models AAAI 2026 Analyzing Finetuning Representation Shift for Multimodal LLMs Steering ICCV 2025 Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution ICLR 2025 CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation COLING 2025 Dehumanization of LGBTQ+ Groups in Sexual Interactions with ChatGPT NAACL 2025 Intrinsic Test of Unlearning Using Parametric Knowledge Traces EMNLP 2025 The Logical Implication Steering Method for Conditional Interventions on Transformer Generation ICML 2025 Unsupervised Concept Vector Extraction for Bias Control in LLMs EMNLP 2025 A Language Model’s Guide Through Latent Space ICML 2024