Toxicity Detection

Ask about this topic

Overview

Toxicity detection covers two related uses: recognizing harmful communication for moderation and predicting adverse effects of chemicals, drugs, or exposures. Language systems range from transformer classifiers and toxic-span taggers to LLM-based reasoning and multimodal speech or image models, with benchmarks such as Civil Comments, ToxiGen, and ToxiREX. Toxicology systems use molecular graph and SMILES models, as well as clinical and imaging data, to estimate endpoint-specific risks on datasets such as Tox21 and ClinTox. Across these settings, open challenges include context-sensitive labels, subgroup fairness, robustness to distribution shifts, reliable explanations, and balancing missed harms against false alarms.

Latest papers

CardsList

46 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. The Punjabi Geet Toxicity Dataset (PGT-FG): Fine-Grained Multimodal Annotations for Toxic Content in Punjabi Songs

    Oct 23, 2026Lakhjeet Kaur, Jaspreet Kaur, Komal Rani +3Multimodal DatasetToxicity Detection

    Department of Computer Science, Guru Gobind Singh Indraprastha University, Delhi, India. · Department of Computer Science, Malwa College Bathinda, Punjab, India. · Department of Management, Akal University Talwandi Sabo, Punjab, India. +3

  2. "You" Is Not Toxic: How LLM Labelers Rewrite the Web's Conversation Laws

    Oct 16, 2026Liang Yue, Eric A. VanceToxicity DetectionLanguage Model Bias Evaluation

    University of Colorado Boulder Boulder, Colorado, USA

  3. In-game Toxic Detection: Bi-directional Representations with Attention Residuals

    Sep 28, 2026Yuanzhe JiaRepresentation LearningToxicity Detection

    University of Sydney, Australia

  4. SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion

    Sep 23, 2026Quang Minh Nguyen, Thuy Quynh Nguyen, Duc Minh Le +3Toxicity DetectionMolecular Property Prediction

    National Economics University Hanoi, Vietnam · VNU University of Science Hanoi, Vietnam

  5. Detoxifying Toxic Communication: A Design Science Approach to Responsible AI

    Aug 31, 2026Hossein Arshadi Soufiani, Henry M. Kim, Hjalmar Turesson +2Toxicity DetectionContent Moderation

    Schulich School of Business, York University

  6. ToxLens: A Reproducible Graph-Learning Framework for Leakage-Aware, Uncertainty-Calibrated Molecular Toxicity Prediction

    Aug 31, 2026Magnus H. Strømme, Alex G. C. de Sá, David B. AscherGraph Representation LearningToxicity Detection

    The Australian Centre for Ecogenomics, School of Chemistry and Molecular Biosciences, The University of Queensland, Brisbane, Queensland, 4072, Australia · Computational Biology and Clinical Informatics, Baker Heart and Diabetes Institute, Melbourne, Victoria, 3004, Australia

  7. An Offline Smartphone Check for Drug Interactions and Past Reactions in Handwritten Prescriptions: A Technical Feasibility Study in Rural Bangladeshi Outpatient Care

    Aug 27, 2026Shahir AbdullahHealthcareClinical Decision Support

    Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh

  8. A Unified DINOv2-Based Framework for LVEF Estimation, GLS Dysfunction Classification, and Early Cardiotoxicity Prediction

    Aug 14, 2026Xiaotong Zhang, Mingyue Cui, Qing Cao +1Left Ventricular Ejection Fraction EstimationToxicity Detection

    Cardiovascular Ultrasound R&D, GE HealthCare, Wuxi, China

  9. AMPBench-MT: A Homology-Controlled Benchmark for Antimicrobial Peptide Potency, Spectrum, and Safety Prediction

    Jul 28, 2026Ziheng Zhou, Huiyu Luo, Xiaohu Zhu +4Benchmark DesignToxicity Detection

    Shanghai Ocean University, Shanghai, China · Tongji University, Shanghai, China · Center for Safe AGI, Shanghai, China +1

  10. Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed

    Jul 27, 2026Xinnuo Xu, Anja Thieme, Daniela Massiceti +6T2I GenerationSafe T2I Generation

    Microsoft Research Cambridge, UK · Microsoft Paris, France

  11. A Scale-adaptive Vision Model Links C. elegans Neuronal Morphology to Behavior for Neurotoxicity Assessment

    Jul 25, 2026Haochao Ying, Shenchong Lv, Yutao Sun +8Vision Foundation ModelsToxicity Detection

    School of Public Health and Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, 310058, China. · State Key Laboratory of Transvascular Implantation Devices and TIDRI, Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, 310009, China. · Polytechnic Institute, Zhejiang University, Hangzhou, 310058, China. +5

  12. Analyzing Toxic Behavior and Its Impact on the Mastodon Community

    Jul 24, 2026Pasan Kamburugamuwa, Scrivner, Olga BSocial Media AnalysisToxicity Detection

    Luddy School of Informatics, Computing, and Engineering Indiana University Bloomington

  13. Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection

    Jul 17, 2026Indraveni Chebolu, Rohan Singh, Arnab Mallick +1Multilingual Language Model EvaluationHate Speech Detection

    Centre for Development of Advanced Computing, Hyderabad, India

  14. Manufactured Divisiveness: Decomposing the Hostile Content of Seven Social Media Influence Operations

    Jul 16, 2026Emilio FerraraSocial Media AnalysisHate Speech Detection

    Thomas Lord Department of Computer Science University of Southern California

  15. EchoRisk: A Multicentre Echocardiography Dataset and Benchmark for Cardio-Oncology

    Jul 1, 2026Grigorios Kalliatakis, Georgia Karanasiou, Georgios Manikis +10Left Ventricular Ejection Fraction EstimationHealthcare

    Foundation for Research and Technology Hellas, Greece · University of Ioannina, Greece · Hellenic Mediterranean University, Greece +3

  16. Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combine

    Jul 1, 2026Jiaxian Lv, Shiyao Cui, Yingkang Wang +3Toxicity DetectionSafety Filtering

    The Conversational AI (CoAI) Group, DCST, Tsinghua University

  17. DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation

    Jun 27, 2026Yuting Xin, Hanyu Cai, Binqi Shen +2Concept DriftContinual Test-Time Adaptation

    Department of Information and Decision Sciences University of Minnesota Minneapolis, USA · Department of Industrial Engineering and Management Sciences Northwestern University Evanston, USA · Fuqua School of Business Duke University Durham, USA +1

  18. ToxiREX: A Dataset on Toxic REasoning in ConteXt

    Jun 26, 2026Stefan F. Schouten, Ilia Markov, Piek VossenLanguage Model Safety EvaluationToxicity Detection

    Vrije Universiteit Amsterdam, the Netherlands

  19. A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models

    Jun 24, 2026Soham Dan, Himanshu Beniwal, Thomas HartvigsenMultilingual Language ModelsLLM Alignment

    Scale AI · Indian Institute of Technology Gandhinagar · University of Virginia

  20. Routine laboratory trajectories encode the onset of organ-level complications in cancer

    Jun 7, 2026Jannik Lübberstedt, Krischan Braitsch, Jacqueline Lammert +21Toxicity DetectionOncology

    Department of Diagnostic and Interventional Radiology, School of Medicine and Health, TUM Klinikum, Rechts der Isar, Technical University of Munich, Germany. · Department of Medicine III, School of Medicine and Health, TUM Klinikum, Rechts der Isar, Technical University of Munich, Germany. · Chair of Medical Informatics, Institute of Artificial Intelligence in Medicine and Healthcare, School of Medicine and Health, TUM Klinikum, Rechts der Isar, Technical University of Munich, Germany. +8

  21. Unsupervised Pattern Analysis in Japanese Veterinary Toxicology: A Regulatory-Compliant Framework for Cross-Species Risk Assessment

    Jun 4, 2026Yukiko Kawakami, Mohammad Shirazi, Ryo Shimizuwa +3Unsupervised ClusteringToxicity Detection

    Tohoku University Graduate School of Medicine, Sendai, Japan · Amirkabir University of Technology, Tehran, Iran · Tohoku University Graduate School of Pharmaceutical Sciences, Sendai, Japan

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

    May 28, 2026Ihor Stepanov, Aleksandr SmechovLanguage Model Safety EvaluationLLM Guardrails

    1Knowledgator, Kyiv, Ukraine · 2Wordcab, New York, USA

  23. Harder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation Rewriting

    May 21, 2026Jingyi Kang, Junyu Lu, Bo Xu +4Language Model Safety EvaluationToxicity Detection

    1Dalian University of Technology · 2The University of Tokyo · 3Singapore University of Technology and Design

  24. Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities

    May 18, 2026Ronja Fuchs, Florian Rupp, Timo Bertram +2Toxicity Detection

    Institute for Information Processing Leibniz University Hannover Hannover, Germany · Department of Computer Science Technische Hochschule Mannheim Mannheim, Germany · Institute for Machine Learning Johannes Kepler University Linz, Austria +1

  25. Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues

    May 15, 2026Zhongjie Ba, Liang Yi, Peng Cheng +3Speech ProcessingHate Speech Detection

    The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou, Zhejiang, China · School of Cyber Science and Engineering, Nanjing University of Science and Technology

  26. Measuring and Mitigating Toxicity in Large Language Models: A Comprehensive Replication Study

    May 13, 2026Mokshit Surana, Archit Rathod, Akshaj SatishkumarLanguage Model Safety EvaluationToxicity Detection

    University of Illinois Chicago

  27. Fair and Calibrated Toxicity Detection with Robust Training and Abstention

    May 13, 2026Mokshit SuranaProbability CalibrationGroup Distributionally Robust Optimization

    University of Illinois Chicago

  28. Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers

    May 11, 2026Nikita Kezins, Urbas Ekka, Pascal Berrang +1Neural Network VerificationLanguage Model Safety Evaluation

    Delft University of Technology · University of Birmingham & Zeroth Research

  29. Automated Detection of Abnormalities in Zebrafish Development

    May 11, 2026Sarath Sivaprasad, Hui-Po Wang, Anna-Lisa Jäckel +4Spatiotemporal TransformersToxicity Detection

    CISPA Helmholtz Center for Information Security, Saarbrücken, Germany · Helmholtz Institute for Pharmaceutical Research Saarland, Saarbrücken, Germany

  30. PSK@EEUCA 2026: Fine-Tuning Large Language Models with Synthetic Data Augmentation for Multi-Class Toxicity Detection in Gaming Chat

    May 8, 2026Srikar Kashyap PulipakaLLM Fine-TuningToxicity Detection

    Independent Researcher