{"ID":2845345,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.10665","arxiv_id":"2511.10665","title":"Guarding the Meaning: Self-Supervised Training for Semantic Robustness in Guard Models","abstract":"Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores, revealing a lack of semantic grounding. To address this, we introduce a practical, self-supervised framework for improving the semantic robustness of guard models. Our method leverages paraphrase sets to enforce prediction consistency using a novel, skew-aware aggregation strategy for robust target computation. Notably, we find that standard aggregation methods like mean and median can degrade safety, underscoring the need for skew-aware alternatives. We analyze six open-source guard models and show that our approach reduces semantic variability across paraphrases by ~58%, improves benchmark accuracy by ~2.5% on average, and generalizes to unseen stylistic variations. Intriguingly, we discover a bidirectional relationship between model calibration and consistency: our robustness training improves calibration by up to 40%, revealing a fundamental connection between these properties. These results highlight the value of treating semantic consistency as a first-class training objective and provide a scalable recipe for building more reliable guard models.","short_abstract":"Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores, revealing a lack of semantic grounding. To address this, we introduce a practical,...","url_abs":"https://arxiv.org/abs/2511.10665","url_pdf":"https://arxiv.org/pdf/2511.10665v1","authors":"[\"Cristina Pinneri\",\"Christos Louizos\"]","published":"2025-11-06T14:15:06Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\"]","has_code":false}