SameFact: The Same Safety Facts Lead to Different Responses Across Interfaces

Reported by arXiv cs.CR (Dongsheng Chen, Jiaxin Zhang, Lei Ma, Xin Yao, Xuetao Wei)

Summary by Cyber Security News30 Sep 2026, 06:00 CEST

About this summary. This is a short, independently written summary of an article first published by arXiv cs.CR. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2609.35872

arXiv:2609.35872v1 Announce Type: new Abstract: Safety evaluations often ask whether a model recognizes that an action is unsafe, whereas agent evaluations ask what the model chooses to do. Using safety judgments as evidence about action selection therefore raises a measurement question: does the influence of the same safety-relevant fact persist across response interfaces? We introduce SameFact, a matched-counterfactual benchmark that tests this question directly.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

Says Block, Still Acts: Why LLM Safety Judgments Fail to Govern Action in LLM Agents

SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents

SaplingGuard: A Multidimensional-Profile-Aware Multi-Agent Guardrail for Developmentally Safe Adolescent-LLM Interaction

Raising the Bar for Chinese Adolescent LLM Safety: A Culturally-Grounded, Fine-Grained Benchmark

Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning

Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery