Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content

• URL: http://arxiv.org/abs/2605.29659v1
• Date: Thu, 28 May 2026 09:21:42 GMT
• Title: Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content
• Abstract summary: Opir is a family of encoder-based guardrail models built on the GLiClass architecture.<n>Opir includes multi-task models for binary safe/unsafe classification, multi-label toxicity classification, jailbreak classification, and zero-shot unsafe prompt and response categorization.
• Score: 46.13517417540154
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak attempts, and unsafe responses without the cost profile of large guardrail models, and that can distinguish benign sensitive text from genuinely covert harmful content. In this paper, we introduce Opir, a family of encoder-based guardrail models built on the GLiClass architecture. Opir includes multi-task models for binary safe/unsafe classification, multi-label toxicity classification, jailbreak classification, and zero-shot unsafe prompt and response categorization. We also release edge variants with fewer than 100M parameters dedicated to binary safe/unsafe categorization. The models are trained on a three-level taxonomy containing 996 categories across 16 top-level labels, 126 mid-level labels, and 854 leaf labels. Opir's training data combines taxonomy-grounded unsafe prompts, adversarially mined hard negatives, benign safety-preserving examples, generated response examples, multilingual translations, and portions of the Aegis2 and WildGuard training subsets. We also open-sourced an evaluation harness that supports GLiClass and GLiNER2 backends as well as decoder-based models, and covers binary safety classification, multi-label categorization, toxicity, jailbreak detection, prompt safety, response safety, response refusal, and prompt subcategory views across public benchmark families. Across an expanded comparison spanning 12 safety-classification tasks and 17 category tasks against eight contemporary guardrail systems -- including both GLiNER2-based and generative guardrail models -- Opir variants are competitive on or ahead of the strongest open-weight baselines on the majority of benchmark datasets while operating with a substantially smaller deployment footprint.

Related papers

• GLiGuard: Schema-Conditioned Classification for LLM Safeguard [5.918280835312565]
  We introduce textbfGLiGuard, a bidirectional encoder adapted from GLiNER2 for LLM content moderation.<n>The key idea is to encode task definitions and label semantics directly into the input sequence as structured token schemas.<n>GLiGuard achieves F1 scores competitive with 7B--27B decoder-based guards despite being 23--90$times$ smaller.
  arXiv  Detail & Related papers  (2026-05-08T16:44:07Z)
• Robust Multimodal Safety via Conditional Decoding [52.92816441364308]
  Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions.<n>We propose a simple conditional decoding strategy, CASA, that utilizes internal representations of MLLMs to predict a binary safety token before response generation.
  arXiv  Detail & Related papers  (2026-03-31T23:19:50Z)
• SGuard-v1: Safety Guardrail for Large Language Models [9.229602223310485]
  SGuard-v1 is a lightweight safety guardrail for Large Language Models (LLMs)<n>It comprises two specialized models to detect harmful content and screen adversarial prompts in human-AI conversational settings.
  arXiv  Detail & Related papers  (2025-11-16T08:15:54Z)
• OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models [54.80460603255789]
  We introduce OutSafe-Bench, the first most comprehensive content safety evaluation test suite designed for the multimodal era.<n>OutSafe-Bench includes a large-scale dataset that spans four modalities, featuring over 18,000 bilingual (Chinese and English) text prompts, 4,500 images, 450 audio clips and 450 videos, all systematically annotated across nine critical content risk categories.<n>In addition to the dataset, we introduce a Multidimensional Cross Risk Score (MCRS), a novel metric designed to model and assess overlapping and correlated content risks across different categories.
  arXiv  Detail & Related papers  (2025-11-13T13:18:27Z)
• Qwen3Guard Technical Report [127.69960525219051]
  We present Qwen3Guard, a series of multilingual safety guardrail models with two specialized variants.<n>Generative Qwen3Guard casts safety classification as an instruction-following task to enable fine-grained tri-class judgments.<n>Stream Qwen3Guard introduces a token-level classification head for real-time safety monitoring.
  arXiv  Detail & Related papers  (2025-10-16T04:00:18Z)
• Scaling behavior of large language models in emotional safety classification across sizes and tasks [0.0]
  We investigate the scaling behavior of large language models (LLMs) on two key tasks: trinary classification of emotional safety and multi-label classification.<n>We construct a novel dataset by merging several human-authored mental health datasets.<n>We evaluate four LLaMA models (1B, 3B, 8B, 70B) across zero-shot, few-shot, and fine-tuning settings.
  arXiv  Detail & Related papers  (2025-09-02T20:53:03Z)
• Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning [58.16354555208417]
  PAD and FFD are proposed to protect face data from physical media-based Presentation Attacks and digital editing-based DeepFakes, respectively.<n>The lack of a Unified Face Attack Detection model to simultaneously handle attacks in these two categories is mainly attributed to two factors.<n>We present a novel Visual-Language Model-based Hierarchical Prompt Tuning Framework that adaptively explores multiple classification criteria from different semantic spaces.
  arXiv  Detail & Related papers  (2025-05-19T16:35:45Z)
• SafeDialBench: A Fine-Grained Safety Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks [90.41592442792181]
  We propose a fine-grained benchmark SafeDialBench for evaluating the safety of Large Language Models (LLMs)<n>Specifically, we design a two-tier hierarchical safety taxonomy that considers 6 safety dimensions and generates more than 4000 multi-turn dialogues in both Chinese and English under 22 dialogue scenarios.<n> Notably, we construct an innovative assessment framework of LLMs, measuring capabilities in detecting, and handling unsafe information and maintaining consistency when facing jailbreak attacks.
  arXiv  Detail & Related papers  (2025-02-16T12:08:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.