pith. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 2

years

2026 1 2025 1

verdicts

UNVERDICTED 2

representative citing papers

The Impact of Off-Policy Training Data on Probe Generalisation

cs.AI · 2025-11-21 · unverdicted · novelty 6.0

Off-policy training data for LLM behavior probes causes significant generalization failures especially for intent-based behaviors like deception, and performance on coerced incentivised data correlates with real on-policy success.

Do Linear Probes Generalize Better in Persona Coordinates?

cs.AI · 2026-05-10 · unverdicted · novelty 5.0 · 2 refs

Persona axes derived from contrastive prompts and PCA yield linear probes that generalize better than raw-activation probes across 10 datasets for deception and sycophancy.

citing papers explorer

Showing 2 of 2 citing papers.

  • The Impact of Off-Policy Training Data on Probe Generalisation cs.AI · 2025-11-21 · unverdicted · none · ref 14

    Off-policy training data for LLM behavior probes causes significant generalization failures especially for intent-based behaviors like deception, and performance on coerced incentivised data correlates with real on-policy success.

  • Do Linear Probes Generalize Better in Persona Coordinates? cs.AI · 2026-05-10 · unverdicted · none · ref 38 · 2 links

    Persona axes derived from contrastive prompts and PCA yield linear probes that generalize better than raw-activation probes across 10 datasets for deception and sycophancy.