Skip to content

Author

Adrians Skapars

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Jul 2026

Probe Generalization as Subspace Selection for OOD Deception Detection

The results suggest that the OOD robustness of probes is largely determined by subspace selection, and projecting inputs onto a small subset of principal components from the training distribution of activations enables cross-domain transfer that nearly matches the performance of probes trained directly on the test dist...

Daniel Yoo, Adrians Skapars · 0 citations
#artificial intelligence Preprint Aug 2026

BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing

BLOOM-WILT is introduced, a full auditing pipeline that elicits natural multi-turn instances of rare behaviours, without training cost or access beyond the target's next-token distribution and raises average behaviour presence from 51% to 100% when eliciting self-harm encouragement from Qwen3.5-4B.

Adrians Skapars, Edoardo Manino · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.