pith. sign in

[24] proposed ShieldHead, a lightweight classification head on last-layer hidden states for decoding-time harmful-content detection, while Zhang et al

show that linear probes over Chain-of-Thought activations can detect unsafe responses before generation, Xuan et al · 1970 · arXiv 7672.4468

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

When is Your LLM Steerable?

cs.CL · 2026-06-10 · unverdicted · novelty 6.0

Early hidden state features from the first few tokens allow a GBDT classifier to predict activation steering success, under-steering, or over-steering with 0.7 macro-F1 on unseen concepts.

citing papers explorer

Showing 1 of 1 citing paper.

  • When is Your LLM Steerable? cs.CL · 2026-06-10 · unverdicted · none · ref 32

    Early hidden state features from the first few tokens allow a GBDT classifier to predict activation steering success, under-steering, or over-steering with 0.7 macro-F1 on unseen concepts.