← Back to all news
arXiv AI By Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta, Denis Kleyko, Mauro Conti, Matteo Zavatteri, Roberto Confalonieri

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

Read the original on arXiv AI →

The paper explores whether a language model’s refusal behavior can be predicted from its intermediate activations before decoding. Using linear probes on residual stream activations at each transformer block, the authors show that refusal signals are linearly decodable well before the final layer, indicating that safety-relevant behavior is encoded early in the network. They then introduce Mechanistic AutoDAN, a probe‑guided variant of AutoDAN that replaces full-model fitness evaluation with partial forward passes and probe-based scoring within a genetic prompt search loop, achieving competitive attack success rates while reducing per‑iteration search time by up to 72% and improving cross‑model transfer in several configurations, especially for larger models.

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.

Related stories

arXiv AI
Sep 7

Harness-agnostic detection and immunization of reward hacking in self-evolving language models

The paper introduces HackProbe, a black‑box monitoring tool that can be attached to any self‑evolving language model loop without accessing internal weights or activations. HackProbe uses a fixed‑distribution comparison core and a rotated fresh layer to detect reward hacking through four statistical tests, and it can immunize the model by selecting honest candidates from the proposal pool. Experiments on a controlled host with injected hacking channels show that HackProbe achieves higher AUROC and lower false‑positive rates than the strongest baseline, and its bandwidth‑limited reselection improves true capability under hacking more than it harms clean runs.

By Rongxin Yang, Yang Liu, Shang Luo, Haoxuan Jia, Chongyang Zhang, Hao Zheng, Yingguang Yang, Yulin Huang, Jianshen Zhang, Yongzhi Qi, Kefu Xu, Congjing Ran, Bin Chong
llms
More like this →
arXiv AI
Jun 8

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

arXiv:2602. 02600v3 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) have recently emerged as a competitive alternative to autoregressive (AR) models, offering parallel decoding, competitive generation quality, and initial evidence of improved jailbreak robustness.

By Eliron Rahimi, Elad Hirshel, Rom Himelstein, Amit LeVi, Avi Mendelson, Chaim Baskin
llmsdiffusionsafety
More like this →