pith. sign in

Language models transmit behavioural traits through hidden signals in data.Nature, 652:615–621, 2026

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

1 Pith paper citing it

fields

cs.CR 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Asking Back: Interaction-Layer Antidistillation Watermarks

cs.CR · 2026-05-15 · unverdicted · novelty 6.0

Interaction-layer antidistillation watermarks use system-prompt-induced behavioral markers like explicit follow-up questions that transfer to distilled student models at 45-89% relative fidelity and can be audited via black-box LLM-as-judge queries.

citing papers explorer

Showing 1 of 1 citing paper.

  • Asking Back: Interaction-Layer Antidistillation Watermarks cs.CR · 2026-05-15 · unverdicted · none · ref 5

    Interaction-layer antidistillation watermarks use system-prompt-induced behavioral markers like explicit follow-up questions that transfer to distilled student models at 45-89% relative fidelity and can be audited via black-box LLM-as-judge queries.