Seduced by the Narrative: Assessing Rule Adherence in Semi-Open Textual Sandboxes

Overview

arXiv:2607.02802v1 Announce Type: new Abstract: As LLMs are increasingly deployed as autonomous adjudicators in semi-open textual game environments, robust rule adherence becomes critical when user intent conflicts with system rules. However, these models are trained to be helpful and compliant, leaving them vulnerable to a class of attacks we term \textit{Rhetorical Injection}, where adversarial users exploit narrative framing techniques such as pseudo-logical reasoning and authoritative coerci

SpinGraph analysis pending — check back after processing.