PrivacySIM shows that conditioning LLMs on user personas like demographics and attitudes improves simulation of privacy choices but reaches only 40.4% accuracy against real responses from 1,000 users.
Privacylens: Evaluating privacy norm awareness of language models in action.Advances in Neural Information Processing Systems, 37:89373–89407
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Vision-language models exhibit perceptual fragility and fail to consistently respect privacy constraints when operating in simulated physical environments, with performance declining in cluttered scenes and under conflicting commands.
citing papers explorer
-
PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior
PrivacySIM shows that conditioning LLMs on user personas like demographics and attitudes improves simulation of privacy choices but reaches only 40.4% accuracy against real responses from 1,000 users.
-
How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study
Vision-language models exhibit perceptual fragility and fail to consistently respect privacy constraints when operating in simulated physical environments, with performance declining in cluttered scenes and under conflicting commands.