Metraipolis › archive › dc_ff65b2149b0d
Why Static Probes Fail: Context Determines Deception Feature Composition — arXiv:2610.27577
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.27577
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:08:57.410Z
- SHA-256 of the archived text
9462de0c25c22f61e09bc69fcb0ac8025d57d876c1d5fe01ca2d674b17934f46- Stable URL of this page
https://metraipolis.com/documento/dc_ff65b2149b0d
How to cite
Why Static Probes Fail: Context Determines Deception Feature Composition — arXiv:2610.27577 — arXiv (en), https://arxiv.org/abs/2610.27577 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff65b2149b0d (Metraipolis archive dc_ff65b2149b0d, sha256 9462de0c25c22f61e09bc69fcb0ac8025d57d876c1d5fe01ca2d674b17934f46)
BibTeX
@misc{dcff65b2149b0d,
title = {Why Static Probes Fail: Context Determines Deception Feature Composition — arXiv:2610.27577},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.27577},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff65b2149b0d; sha256 9462de0c25c22f61e09bc69fcb0ac8025d57d876c1d5fe01ca2d674b17934f46},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27577. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
With increasing autonomy, Large Language Models (LLMs) may engage in deceptive behaviors, such as scheming to pursue misaligned goals or sandbagging to escape oversight. Monitoring outputs alone is insufficient, as models can produce seemingly benign responses while harboring misaligned internal objectives. While mechanistic approaches like linear probing are promising, they rely on the assumption that deception corresponds to a single direction in representation space. We demonstrate that such single-direction probes fail to generalize across diverse deception scenarios. To bridge this gap, we propose representing deception as a multi-dimensional subspace rather than a single direction. Our method utilizes iterative orthogonal decomposition to identify complementary directions that capture distinct facets of deceptive intent. To effectively leverage these directions for detection, we find that static combinations prove brittle due to strong domain dependence across different scenarios. We therefore introduce a domain-adaptive gating mechanism that dynamically composes the extracted directions through few-shot adaptation at test time. With only 10 examples, our approach achieves an average AUROC of 0.97 and 94% recall at 5% FPR across all evaluated datasets, substantially outperforming existing methods. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.27577 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-21T07:05:58.120Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).