Frontier LLMs leak prompted secret information thematically in generated stories at rates up to 79% above chance in binary discrimination tests, even when told to hide it, with leakage scaling by model size and vanishing for short-form outputs.
Has my system prompt been used? Large language model prompt membership inference.arXiv preprint arXiv:2502.09974
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.
citing papers explorer
-
Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing
Frontier LLMs leak prompted secret information thematically in generated stories at rates up to 79% above chance in binary discrimination tests, even when told to hide it, with leakage scaling by model size and vanishing for short-form outputs.
-
Prompt Governance? On Governing Technologies Governed by Natural Language
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.