Ning Ma

Agents can exhibit deceptive behavior even when they know a user's entitlement, revealing a critical vulnerability in LLM deployment under conflicting incentives.

LLMs that nail individual personas can still fail spectacularly at generating diverse populations, instead defaulting to coarse stereotypes.

LLMs leak significantly more private information in multi-turn conversations than single-message evaluations suggest, and free-text pseudonymization offers a more robust privacy-utility trade-off than suppression or generalization.