PrincipalBench exposes a sharp split in frontier LLMs between selective and over-refusing behavior on multi-party loyalty, with prompt scaffolding and KL distillation reducing harm rates but only along an existing leak/over-refusal trade-off.
Can llms keep a secret? testing privacy implications of language models via contextual integrity theory
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
verdicts
UNVERDICTED 9representative citing papers
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.
Users show curiosity over concern toward LLM inferences of personal information, with acceptability depending on context, alignment with expectations, and who uses the inferences rather than just the content.
CAMP formalizes Cumulative PII Exposure and uses a session registry, co-occurrence graph, and CPE score to trigger retroactive masking in multi-turn LLM conversations, neutralizing re-identifiable profiles in synthetic tests while keeping utility intact.
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
PrivScope enforces task-scoped disclosure at the local-cloud boundary in hybrid agents, eliminating profile leakage and halving re-identification risk on medical workflows while preserving task success.
AgentCollabBench shows that multi-agent reliability is limited by communication topology, with converging-DAG nodes causing synthesis bottlenecks that discard constraints and explain 7-40% of information loss variance.
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.
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.
citing papers explorer
-
Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents
PrincipalBench exposes a sharp split in frontier LLMs between selective and over-refusing behavior on multi-party loyalty, with prompt scaffolding and KL distillation reducing harm rates but only along an existing leak/over-refusal trade-off.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.