arXiv Machine Learning
How Far Can You Steer? Behavior-Capability Frontiers in Contrastive Activation Addition
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
2d ago
How Far Can You Steer? Behavior-Capability Frontiers in Contrastive Activation Addition
Activation steering can modify language-model behavior without parameter updates, but behavioral efficacy alone does not determine whether an intervention is usable. Contrastive Activation Addition (C...
arXiv AI
Oct 27
CANS: Capability-Preserving Neuron Steering for Large Language Models
arXiv:2610.35530v1 Announce Type: new Abstract: Activation steering offers training-free and dynamic control of target behaviors in large language models, but existing methods can impair general capa...
arXiv AI
Jul 29
Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
arXiv Computation and Language
Oct 21
RealControlBench: A Benchmark for Interpretability-Informed Fine-Grained Control of LLMs and Agents
RealControlBench is a new benchmark that evaluates fine‑grained steering of large language models and agents across diverse behavioral targets and interaction settings. It extends beyond isolated generation tasks to include complex, execution‑grounded, multi‑turn agent interactions, covering instruction‑following control, tool‑use decision control, reasoning performance, reasoning length, and safety awareness. The benchmark jointly measures target controllability and capability preservation, testing robustness across prompts, domains, and model architectures, and finds that current steering methods are often unreliable in realistic scenarios.
arXiv Machine Learning
Jun 9
Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior
arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.
arXiv Machine Learning
Aug 7
Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study
arXiv:2608. 05164v1 Announce Type: cross Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested.