conftrace_

steering vector

39 papers

Explore in graph

Also known as

SV

Co-occurring keywords · papers mentioning both

large language model (19) sparse autoencoder (6) language model (4) activation steering (3) model steering (3) hallucination mitigation (3) model interpretability (3) chain-of-thought reasoning (3) activation editing (2) inference time (2)

Papers

Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders ACL 2025 Activation Scaling for Steering and Interpreting Language Models EMNLP 2024 Analysing the Generalisation and Reliability of Steering Vectors NeurIPS 2024 Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective EMNLP 2024 InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance EMNLP 2024 Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization NeurIPS 2024 Steering Llama 2 via Contrastive Activation Addition ACL 2024 The Linear Representation Hypothesis and the Geometry of Large Language Models ICML 2024 Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models ACL 2024 Word Embeddings Are Steers for Language Models ACL 2024 Self-Detoxifying Language Models via Toxification Reversal EMNLP 2023 Steering vector correction in MVDR beamformer for speech enhancement Interspeech 2022 A Novel Method to Correct Steering Vectors in MVDR Beamformer for Noise Robust ASR Interspeech 2019 Improved MVDR Beamforming Using Single-Channel Mask Prediction Networks Interspeech 2016