Polarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial Framing

Summary

Researchers study "polarity blindness," a failure where LLMs miss harmful intent after grammatical negation or antonym replacement, using synonym replacement as a control. They test 260 prompts across 10 LLMs in English, Spanish and Czech, rated on a validated 0-5 harm scale, and whether an adversarial textual wrapper amplifies the effect. Polarity blindness affects most evaluated models, with mean harm scores reaching 4.12 for the most vulnerable one, and it persists across typologically different negation systems.

Related items

• InfoBuilding Trust into Enterprise AI Agents: Cisco AI Defense and Workday Agent PassportSimilar attack · Cisco AI Blog
• InfoABench: Adversarily Benchmarking Large Language Models across Taxonomized ValuesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoOrthogonal Boundary Unlearning for Dual-Use Concepts in Large Language ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoGlobal Security Blind Spots: Translation as a Safety Bypass in Low-Resource LanguagesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoSafety Mid-Training: Internalizing LLM Safety as a Foundational CapabilitySimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)