{"total":55,"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":"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":"2102.05456","title":"Civil Rephrases Of Toxic Texts With Self-Supervised Transformers","created":"2021-02-01","cited_by_count":32,"area":null},{"id":"2201.08643","title":"Text Style Transfer for Bias Mitigation using Masked Language Modeling","created":"2022-01-21","cited_by_count":28,"area":null},{"id":"2209.08207","title":"APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations","created":"2022-09-17","cited_by_count":23,"area":null},{"id":"2109.15144","title":"A Review of Text Style Transfer using Deep Learning","created":"2021-09-30","cited_by_count":18,"area":null},{"id":"2204.07359","title":"Text Revision by On-the-Fly Representation Optimization","created":"2022-04-15","cited_by_count":17,"area":null},{"id":"2206.04007","title":"Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization","created":"2022-06-08","cited_by_count":17,"area":null},{"id":"2301.11997","title":"Prompt-Based Editing for Text Style Transfer","created":"2023-01-27","cited_by_count":16,"area":null},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2311.13937","title":"Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification","created":"2023-11-23","cited_by_count":15,"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":"2404.02037","title":"MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages","created":"2024-04-02","cited_by_count":14,"area":null},{"id":"2105.09052","title":"Methods for Detoxification of Texts for the Russian Language","created":"2021-05-19","cited_by_count":13,"area":null},{"id":"2112.11739","title":"A Survey of Natural Language Generation","created":"2021-12-22","cited_by_count":13,"area":null},{"id":"2109.02941","title":"Countering Online Hate Speech: An NLP Perspective","created":"2021-09-07","cited_by_count":12,"area":null},{"id":"2109.04624","title":"Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness","created":"2021-09-10","cited_by_count":12,"area":null},{"id":"2109.07812","title":"Transductive Learning for Unsupervised Text Style Transfer","created":"2021-09-16","cited_by_count":12,"area":null},{"id":"2412.11691","title":"Multilingual and Explainable Text Detoxification with Parallel Corpora","created":"2024-12-16","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":"2111.12447","title":"Revisiting Contextual Toxicity Detection in Conversations","created":"2021-11-24","cited_by_count":8,"area":null},{"id":"2312.14708","title":"Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising","created":"2023-12-22","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":"2305.14755","title":"Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2306.08505","title":"DiffuDetox: A Mixed Diffusion Model for Text Detoxification","created":"2023-06-14","cited_by_count":6,"area":"diffusion"},{"id":"2404.14695","title":"MisgenderMender: A Community-Informed Approach to Interventions for Misgendering","created":"2024-04-23","cited_by_count":6,"area":null},{"id":"2103.13439","title":"StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commands","created":"2021-03-24","cited_by_count":5,"area":null},{"id":"2110.15871","title":"From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey","created":"2021-10-29","cited_by_count":5,"area":null},{"id":"2310.18830","title":"Translating away Translationese without Parallel Data","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2407.14822","title":"Text Style Transfer: An Introductory Overview","created":"2024-07-20","cited_by_count":5,"area":null},{"id":"2410.13641","title":"An Active Learning Framework for Inclusive Generation by Large Language Models","created":"2024-10-17","cited_by_count":5,"area":"distill"},{"id":"2212.09670","title":"StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer","created":"2022-12-19","cited_by_count":4,"area":null},{"id":"2502.06394","title":"SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators","created":"2025-02-10","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":"2507.15557","title":"Evaluating Text Style Transfer: A Nine-Language Benchmark for Text Detoxification","created":"2025-07-21","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":"2410.20298","title":"Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data","created":"2024-10-27","cited_by_count":3,"area":"alignment"},{"id":"2112.01062","title":"Syntax Customized Video Captioning by Imitating Exemplar Sentences","created":"2021-12-02","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":"2304.09865","title":"Safer Conversational AI as a Source of User Delight","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2309.10929","title":"Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training","created":"2023-09-19","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":"2108.07871","title":"Contextualizing Variation in Text Style Transfer Datasets","created":"2021-08-17","cited_by_count":1,"area":null},{"id":"2204.10195","title":"IIITDWD-ShankarB@ Dravidian-CodeMixi-HASOC2021: mBERT based model for identification of offensive content in south Indian languages","created":"2022-04-13","cited_by_count":1,"area":null},{"id":"2208.05757","title":"A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deception","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2410.14894","title":"Soft-Label Integration for Robust Toxicity Classification","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2507.04350","title":"HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2101.06172","title":"Empirical Evaluation of Supervision Signals for Style Transfer Models","created":"2021-01-15","cited_by_count":0,"area":null},{"id":"2406.19543","title":"Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2407.15556","title":"SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2407.16737","title":"A Survey of Text Style Transfer: Applications and Ethical Implications","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2510.01250","title":"GemDetox at TextDetox CLEF 2025: Enhancing a Massively Multilingual Model for Text Detoxification on Low-resource Languages","created":"2025-09-24","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}],"next_cursor":null}