{"total":24,"rows":[{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198,"area":null},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2404.11457","title":"Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era","created":"2024-04-17","cited_by_count":98,"area":null},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42,"area":null},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2202.08011","title":"Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks","created":"2022-02-16","cited_by_count":36,"area":null},{"id":"2209.03463","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","created":"2022-09-07","cited_by_count":33,"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":"2310.14424","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","created":"2023-10-22","cited_by_count":18,"area":null},{"id":"2212.10557","title":"DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2305.13973","title":"Effortless Integration of Memory Management into Open-Domain Conversation Systems","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2311.17376","title":"CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2401.09248","title":"Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2407.11203","title":"The Life Cycle of Large Language Models: A Review of Biases in Education","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2412.16469","title":"Chained Tuning Leads to Biased Forgetting","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2211.10596","title":"Bipartite-play Dialogue Collection for Practical Automatic Evaluation of Dialogue Systems","created":"2022-11-19","cited_by_count":1,"area":null},{"id":"2212.02745","title":"Sources of Noise in Dialogue and How to Deal with Them","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2305.15757","title":"Healing Unsafe Dialogue Responses with Weak Supervision Signals","created":"2023-05-25","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":"2410.19812","title":"Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2402.00446","title":"Improving Dialog Safety using Socially Aware Contrastive Learning","created":"2024-02-01","cited_by_count":0,"area":null},{"id":"2509.10833","title":"Towards Automated Error Discovery: A Study in Conversational AI","created":"2025-09-13","cited_by_count":0,"area":null}],"next_cursor":null}