Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Stepanov, Ihor, Smechov, Aleksandr
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction Tasks
por: Stepanov, Ihor, et al.
Publicado: (2024)

GLiClass: Generalist Lightweight Model for Sequence Classification Tasks
por: Stepanov, Ihor, et al.
Publicado: (2025)

Towards Generalizable Generic Harmful Speech Datasets for Implicit Hate Speech Detection
por: Almohaimeed, Saad, et al.
Publicado: (2025)

Efficient Safety Retrofitting Against Jailbreaking for LLMs
por: Garcia-Gasulla, Dario, et al.
Publicado: (2025)

Toxicity Detection Should Measure Contextual Harm, Not Text-Intrinsic Badness
por: Berezin, Sergei, et al.
Publicado: (2025)

Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration
por: Fillies, Jan, et al.
Publicado: (2025)

Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI
por: Böck, Adrian Jaques, et al.
Publicado: (2024)

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
por: Chan, Yik Siu, et al.
Publicado: (2025)

Dealing with Annotator Disagreement in Hate Speech Classification
por: Dehghan, Somaiyeh, et al.
Publicado: (2025)

Investigating Annotator Bias in Large Language Models for Hate Speech Detection
por: Das, Amit, et al.
Publicado: (2024)

Causality Guided Representation Learning for Cross-Style Hate Speech Detection
por: Zhao, Chengshuai, et al.
Publicado: (2025)

Detecting Hope, Hate, and Emotion in Arabic Textual Speech and Multi-modal Memes Using Large Language Models
por: AlDahoul, Nouar, et al.
Publicado: (2025)

Parameter-Efficient Fine-Tuning for Low-Resource Languages: A Comparative Study of LLMs for Bengali Hate Speech Detection
por: Islam, Akif, et al.
Publicado: (2025)

Transformers and Ensemble methods: A solution for Hate Speech Detection in Arabic languages
por: de Paula, Angel Felipe Magnossão, et al.
Publicado: (2023)

Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales
por: Nirmal, Ayushi, et al.
Publicado: (2024)

Large Language Models in the Task of Automatic Validation of Text Classifier Predictions
por: Tsymbalov, Aleksandr, et al.
Publicado: (2025)

Identifying False Content and Hate Speech in Sinhala YouTube Videos by Analyzing the Audio
por: Wickramaarachchi, W. A. K. M., et al.
Publicado: (2024)

PromptScreen: Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline
por: Rao, Akshaj Prashanth, et al.
Publicado: (2025)

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors
por: Chaudhary, Maheep, et al.
Publicado: (2025)

Multilingual Hate Speech Detection in Social Media Using Translation-Based Approaches with Large Language Models
por: Usman, Muhammad, et al.
Publicado: (2025)

1-800-SHARED-TASKS @ NLU of Devanagari Script Languages: Detection of Language, Hate Speech, and Targets using LLMs
por: Purbey, Jebish, et al.
Publicado: (2024)

UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models
por: Oh, Sejoon, et al.
Publicado: (2024)

Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks
por: Cheng, Yixin, et al.
Publicado: (2024)

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
por: Andriushchenko, Maksym, et al.
Publicado: (2024)

NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models
por: Ye, Yiran, et al.
Publicado: (2023)

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
por: Pandey, Punya Syon, et al.
Publicado: (2025)

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
por: Liu, Kangwei, et al.
Publicado: (2025)

Jailbreaking with Universal Multi-Prompts
por: Hsu, Yu-Ling, et al.
Publicado: (2025)

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures
por: Gringras, David
Publicado: (2026)

Best-of-N Jailbreaking
por: Hughes, John, et al.
Publicado: (2024)

BiasJailbreak:Analyzing Ethical Biases and Jailbreak Vulnerabilities in Large Language Models
por: Lee, Isack, et al.
Publicado: (2024)

Whitening Not Recommended for Classification Tasks in LLMs
por: Forooghi, Ali, et al.
Publicado: (2024)

OSPC: Artificial VLM Features for Hateful Meme Detection
por: Grönquist, Peter
Publicado: (2024)

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
por: Chen, Taiye, et al.
Publicado: (2025)

Semi-Supervised Learning for Large Language Models Safety and Content Moderation
por: Dinuta, Eduard Stefan, et al.
Publicado: (2025)

Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing
por: Neill, James O', et al.
Publicado: (2025)

OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy
por: Wang, Haowen, et al.
Publicado: (2024)

Lightweight Safety Classification Using Pruned Language Models
por: Sawtell, Mason, et al.
Publicado: (2024)

Keyword Extraction, and Aspect Classification in Sinhala, English, and Code-Mixed Content
por: Rizvi, F. A., et al.
Publicado: (2025)

Mitigating Extrinsic Gender Bias for Bangla Classification Tasks
por: Joy, Sajib Kumar Saha, et al.
Publicado: (2024)