Behavioral canaries detect unauthorized RL fine-tuning on private contexts by inducing and measuring trigger-conditioned stylistic preferences, achieving 67% detection at 10% false-positive rate with 1% injection.
Llm dataset infer- ence: Did you train on my dataset? In A
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A new sequential interaction framework lets LLMs propose questions to forums, with simulations on real Stack Exchange data showing players can reach roughly half the utility of an ideal full-information scenario despite incentive misalignment.
citing papers explorer
-
Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
Behavioral canaries detect unauthorized RL fine-tuning on private contexts by inducing and measuring trigger-conditioned stylistic preferences, achieving 67% detection at 10% false-positive rate with 1% injection.
-
From Competition to Collaboration: Designing Sustainable Mechanisms Between LLMs and Online Forums
A new sequential interaction framework lets LLMs propose questions to forums, with simulations on real Stack Exchange data showing players can reach roughly half the utility of an ideal full-information scenario despite incentive misalignment.