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: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:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
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: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: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.
arXiv:2606. 08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs).
arXiv:2610.07722v1 Announce Type: new Abstract: Activation steering provides a lightweight and flexible way to control large language model (LLM) behavior. However, effective steering requires more t...
arXiv:2608. 01548v2 Announce Type: replace Abstract: Language-first intelligence is constrained by which distinctions enter its symbolic record, which mappings its language--interpreter--environment complex can execute, and which possibilities can be realized with finite resources.
arXiv:2602.09870v3 Announce Type: replace Abstract: Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized t...
The paper investigates a specific failure mode in vision‑language‑action models, termed instruction‑action binding, where models respond to language and vision separately but fail to combine them to select the correct action under counterfactual changes. Through behavioral analyses of fine‑tuned policies, the authors show that failed rollouts often preserve source behavior or switch to other demonstrated tasks, indicating that language is not ignored but mis‑bound. They propose Equivariant Counterfactual Training (ECT), which supplies counterfactual demonstrations and a paired loss to enforce correct action selection, achieving significant performance gains across simulated and real‑world benchmarks.
FLIP is a final‑layer inference‑time probe designed to test whether a logit‑facing intervention site in an open‑weight vision‑language model (VLM) supports structured, task‑linked computation rather than generic perturbation. The probe applies elementwise flooring to the final normalized hidden state before logit computation, leaving other model components unchanged. By sweeping intervention strength on a controlled detection/counting task, FLIP identifies three regimes—negligible change, a bounded interior regime with improved detection recall and reduced counting error, and over‑suppression—while a four‑criterion protocol ensures the observed effects are mechanistically interpretable.