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

Negation remains a persistent challenge for language models across NLP tasks and modalities.

By Lozano, Derner, Pérez-Ortiz +1Oct 20, 2026

Score████░░░░░░4.1

Caveats

Preprint; not yet peer reviewed.

VerdictWorth a reader's time today.

Read the original PDF Code

Abstract

Negation remains a persistent challenge for language models across NLP tasks and modalities. We show that this weakness can undermine LLM safety guardrails through a structural vulnerability we term polarity blindness: the failure to recognize harmful intent after polarity-altering linguistic transformations. We study two forms of polarity inversion: grammatical negation and antonym replacement, and use synonym replacement as a polarity-preserving control. We further test whether an adversarial textual wrapper amplifies these failures. Using a 260-prompt benchmark across 10 state-of-the-art LLMs and 3 languages (English, Spanish, Czech), stratified by harmfulness potential and evaluated on a validated 0-5 harm scale, we find that polarity blindness affects most evaluated models, with mean harm scores reaching 4.12 for the most vulnerable model. The effect persists across typologically differing negation systems, suggesting that polarity blindness reflects a broader limitation in semantic robustness rather than a language- or grammar-specific failure.

Diego Miguel Lozano, Erik Derner, Juan Antonio Pérez-Ortiz, Nuria Oliver

The editor's rubric

Heuristic review

Leverage4 / 5: A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing).; 24% of this desk’s rubric
Magnitude3 / 5: Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.; 18% of this desk’s rubric
Evidence3 / 5: Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.; 14% of this desk’s rubric
Novelty3 / 5: A genuinely new approach to an open problem.; 16% of this desk’s rubric
Trajectory3 / 5: A clear path to scale.; 18% of this desk’s rubric
Stakes2 / 5: Benefits a professional community (practitioners, clinicians, engineers).; 10% of this desk’s rubric

Dimension	Level	Weight	What that level means
Leverage	████░ 4	24%	A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing).
Magnitude	███░░ 3	18%	Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.
Evidence	███░░ 3	14%	Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.
Novelty	███░░ 3	16%	A genuinely new approach to an open problem.
Trajectory	███░░ 3	18%	A clear path to scale.
Stakes	██░░░ 2	10%	Benefits a professional community (practitioners, clinicians, engineers).

Editor’s rationale

Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we report); breadth (many tasks); gains (state of the art); novelty (alternative to status quo); verification (error bars, multiple benchmarks, experimental validation); scale (scalable); stakes (general AI).

How the score was computed

rank-2026-10-18

Score████░░░░░░4.1

Score = 10 × (65% × adjusted merit / 10 + 25% × attention + 10% × freshness)

Desks place stronger verdicts first, then use this score to order work within the same verdict.

Merit: 6.3 / 10; Weighted rubric, evidence-gated.
Adjusted merit: 5.1 / 10; Shrunk toward the desk prior by editor confidence (48%).
Attention: 0%; Citations, upvotes, points, mentions.
Freshness: 79%; Half-life decay since publication.

No attention signals recorded yet.

The record

Reviewed by heuristic-v7 on Oct 21, 2026, 05:16 UTC. Paper type: method.
Categories: cs.CL, cs.AI
BRIEF, No.2 in the Artificial Intelligence edition of October 21, 2026.