arxiv
PublishedJuly 18, 2026 at 4:00 AM
—neutral
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity
Publisher summary· verbatim
arXiv:2607.01153v2 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an instruction, refused appropriately, complied with a policy, resisted an embedded command, or m
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivADS-C: Antidistillation Sampling for Classification23harxivTesting Distributions Against Bounded Distinguishers23harxivFrom Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems23harxivA Formally Grounded ODRL Evaluator: Implementation and Comparison23hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗