{"total":26,"rows":[{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2109.08914","title":"Text Detoxification using Large Pre-trained Neural Models","created":"2021-09-18","cited_by_count":52,"area":null},{"id":"2308.05596","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","created":"2023-08-10","cited_by_count":39,"area":null},{"id":"2212.10543","title":"Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts","created":"2022-12-20","cited_by_count":36,"area":null},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22,"area":null},{"id":"2403.20103","title":"NLP for Counterspeech against Hate: A Survey and How-To Guide","created":"2024-03-29","cited_by_count":22,"area":null},{"id":"2302.09270","title":"Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements","created":"2023-02-18","cited_by_count":14,"area":null},{"id":"2306.00539","title":"A Call for Standardization and Validation of Text Style Transfer Evaluation","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2311.10781","title":"Can Language Model Moderators Improve the Health of Online Discourse?","created":"2023-11-16","cited_by_count":12,"area":null},{"id":"2402.15951","title":"DetoxLLM: A Framework for Detoxification with Explanations","created":"2024-02-25","cited_by_count":10,"area":null},{"id":"2208.00176","title":"ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trolls","created":"2022-07-30","cited_by_count":7,"area":null},{"id":"2406.03363","title":"LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2210.07595","title":"The State of Profanity Obfuscation in Natural Language Processing","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2506.01484","title":"LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2206.02252","title":"Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models","created":"2022-06-05","cited_by_count":3,"area":null},{"id":"2112.08346","title":"Simple Text Detoxification by Identifying a Linear Toxic Subspace in Language Model Embeddings","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2205.08814","title":"Exploiting Social Media Content for Self-Supervised Style Transfer","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2405.09948","title":"Mitigating Text Toxicity with Counterfactual Generation","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2304.01890","title":"Sociocultural knowledge is needed for selection of shots in hate speech detection tasks","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2511.01512","title":"BanglaNirTox: A Large-scale Parallel Corpus for Explainable AI in Bengali Text Detoxification","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2307.04892","title":"Entity Identifier: A Natural Text Parsing-based Framework For Entity Relation Extraction","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2311.09680","title":"Trustworthy Large Models in Vision: A Survey","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2604.12770","title":"Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2607.07318","title":"R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}