{"total":45,"rows":[{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"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":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","cited_by_count":33,"area":null},{"id":"2312.11523","title":"ToViLaG: Your Visual-Language Generative Model is Also An Evildoer","created":"2023-12-13","cited_by_count":27,"area":null},{"id":"2401.04531","title":"MERA: A Comprehensive LLM Evaluation in Russian","created":"2024-01-09","cited_by_count":22,"area":null},{"id":"2405.11724","title":"Token-wise Influential Training Data Retrieval for Large Language Models","created":"2024-05-20","cited_by_count":20,"area":null},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18,"area":null},{"id":"2406.15586","title":"TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings","created":"2024-06-21","cited_by_count":17,"area":null},{"id":"2407.15366","title":"Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias","created":"2024-07-22","cited_by_count":17,"area":null},{"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":"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":"2404.02037","title":"MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages","created":"2024-04-02","cited_by_count":14,"area":null},{"id":"2403.01106","title":"Distilling Text Style Transfer With Self-Explanation From LLMs","created":"2024-03-02","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":"2210.10329","title":"Language Detoxification with Attribute-Discriminative Latent Space","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2402.07767","title":"Text Detoxification as Style Transfer in English and Hindi","created":"2024-02-12","cited_by_count":11,"area":null},{"id":"2305.14016","title":"Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine Translation","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2304.11220","title":"Learn What NOT to Learn: Towards Generative Safety in Chatbots","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2506.01790","title":"IF-GUIDE: Influence Function-Guided Detoxification of LLMs","created":"2025-06-02","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":"2308.08295","title":"CMD: a framework for Context-aware Model self-Detoxification","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2404.14695","title":"MisgenderMender: A Community-Informed Approach to Interventions for Misgendering","created":"2024-04-23","cited_by_count":6,"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":"2406.17566","title":"FrenchToxicityPrompts: a Large Benchmark for Evaluating and Mitigating Toxicity in French Texts","created":"2024-06-25","cited_by_count":5,"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":"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":"2404.12933","title":"Cross-cultural Inspiration Detection and Analysis in Real and LLM-generated Social Media Data","created":"2024-04-19","cited_by_count":3,"area":null},{"id":"2408.07873","title":"Words Matter: Reducing Stigma in Online Conversations about Substance Use with Large Language Models","created":"2024-08-15","cited_by_count":3,"area":null},{"id":"2404.03052","title":"GPT-DETOX: An In-Context Learning-Based Paraphraser for Text Detoxification","created":"2024-04-03","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":"2407.00740","title":"LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2506.13513","title":"K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2509.07588","title":"BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2204.13638","title":"Russian Texts Detoxification with Levenshtein Editing","created":"2022-04-28","cited_by_count":1,"area":null},{"id":"2507.10177","title":"Detoxify: A framework for abusive text transformation using LLMs","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.18769","title":"ylmmcl at Multilingual Text Detoxification 2025: Lexicon-Guided Detoxification and Classifier-Gated Rewriting","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2507.23319","title":"What's Taboo for You? - An Empirical Evaluation of LLMs Behavior Toward Sensitive Content","created":"2025-07-31","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":"2511.06391","title":"HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2604.19124","title":"Detoxification for LLM: From Dataset Itself","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2609.00361","title":"Detoxifying Toxic Communication: A Design Science Approach to Responsible AI","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}