pith. machine review for the scientific record. sign in

Language models may verbatim complete text they were not explicitly trained on

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

Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs

cs.CR · 2026-04-20 · unverdicted · novelty 7.0

Indistinguishability-based privacy is incomparable to extractability in LLMs, and a new (l, b)-inextractability definition with rank-based bounds provides a tighter measure of extraction risk than prior proxies.

citing papers explorer

Showing 1 of 1 citing paper.

  • Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs cs.CR · 2026-04-20 · unverdicted · none · ref 22

    Indistinguishability-based privacy is incomparable to extractability in LLMs, and a new (l, b)-inextractability definition with rank-based bounds provides a tighter measure of extraction risk than prior proxies.