arXiv Machine Learning
Disentangling Steering Vectors
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
1d ago
Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
arXiv:2602.01654v2 Announce Type: replace Abstract: Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing...
arXiv AI
Jul 13
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.
Hugging Face Trending Papers
Aug 13
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferred from observed model behavior and computational inefficiency from collecting such behavioral evidence at scale.
arXiv Machine Learning
Aug 5
Inverted Detection and Control in Steering Vectors
arXiv:2608. 02957v1 Announce Type: new Abstract: Steering vectors (SVs) are widely used to influence the expression of concepts (e.
arXiv Computation and Language
1d ago
Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation
arXiv:2606.18389v2 Announce Type: replace Abstract: Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated dat...
arXiv Computation and Language
1d ago
Calibrating Lightweight Sparse Autoencoder Feature Steering
arXiv:2506.12576v3 Announce Type: replace Abstract: Sparse autoencoders (SAEs) can enable inference-time topic steering by modifying latent feature activations, but existing steering methods often fa...