arXiv:2509. 13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2608. 06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines.
arXiv:2609.06289v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inferenc...
arXiv:2610.00601v1 Announce Type: cross Abstract: Reasoning-enabled VLA policies expose chain-of-thought (CoT) traces that appear to explain and guide their actions, creating a potential interface fo...
arXiv:2608. 08383v1 Announce Type: cross Abstract: Steering vectors are a lightweight tool for controlling LLM behavior.
arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
The paper introduces CAM-Steer, a Category‑Adaptive Multi‑category Safety Steering framework that estimates risk for each harm category by comparing hidden states to safe and unsafe prototypes. It then combines safety directions into a single steering vector and applies a rotation whose angle is set by the estimated risks, preserving the hidden‑state norm. Experiments on three LLM backbones and seven harm categories show that CAM‑Steer outperforms baselines in defense success rate, even when multiple harm categories co‑occur, with negligible inference overhead.