toxic content

Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification ACL 2026 To Paraphrase or Not: Efficient Comment Detoxification with Unsupervised Detoxifiability Discrimination EACL 2026 Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization EMNLP 2025 Curiosity-driven Red-teaming for Large Language Models ICLR 2024 Down the Toxicity Rabbit Hole: A Framework to Bias Audit Large Language Models with Key Emphasis on Racism, Antisemitism, and Misogyny IJCAI 2024 Exploring the Emotional Dimension of French Online Toxic Content COLING 2024 Improving Dialog Safety using Socially Aware Contrastive Learning EACL 2024 Unlearning Traces the Influential Training Data of Language Models ACL 2024 BiasX: “Thinking Slow” in Toxic Content Moderation with Explanations of Implied Social Biases EMNLP 2023 COUNT: COntrastive UNlikelihood Text Style Transfer for Text Detoxification EMNLP 2023 ToViLaG: Your Visual-Language Generative Model is Also An Evildoer EMNLP 2023 Measuring Harmful Representations in Scandinavian Language Models EMNLP 2022 Moderating Our (Dis)Content: Renewing the Regulatory Approach EMNLP 2020 Online abuse detection: the value of preprocessing and neural attention models NAACL 2019