{"total":29,"rows":[{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87,"area":null},{"id":"2311.14479","title":"Controlled Text Generation via Language Model Arithmetic","created":"2023-11-24","cited_by_count":51,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"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":"2311.07167","title":"STEER: Unified Style Transfer with Expert Reinforcement","created":"2023-11-13","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":"2305.12785","title":"MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space","created":"2023-05-22","cited_by_count":12,"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":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2402.13462","title":"Potential and Challenges of Model Editing for Social Debiasing","created":"2024-02-21","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":"2401.16457","title":"Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters","created":"2024-01-29","cited_by_count":8,"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":"2404.14695","title":"MisgenderMender: A Community-Informed Approach to Interventions for Misgendering","created":"2024-04-23","cited_by_count":6,"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":"2311.05451","title":"All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation","created":"2023-11-09","cited_by_count":3,"area":null},{"id":"2511.09292","title":"C$^3$TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2604.14602","title":"CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2405.09948","title":"Mitigating Text Toxicity with Counterfactual Generation","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2506.08188","title":"GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2401.08491","title":"Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2402.08968","title":"GrounDial: Human-norm Grounded Safe Dialog Response Generation","created":"2024-02-14","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":"2402.15202","title":"Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models","created":"2024-02-23","cited_by_count":0,"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":"2604.19124","title":"Detoxification for LLM: From Dataset Itself","created":"2026-04-21","cited_by_count":0,"area":null}],"next_cursor":null}