{"total":109,"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":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244,"area":"alignment"},{"id":"2310.17884","title":"Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory","created":"2023-10-27","cited_by_count":230,"area":null},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2212.10465","title":"SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization","created":"2022-12-20","cited_by_count":168,"area":null},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2401.13136","title":"The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts","created":"2024-01-23","cited_by_count":94,"area":"alignment"},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2305.02750","title":"A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects","created":"2023-05-04","cited_by_count":66,"area":null},{"id":"2406.17626","title":"CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference","created":"2024-06-25","cited_by_count":51,"area":"safety"},{"id":"2404.12670","title":"Towards Human-centered Proactive Conversational Agents","created":"2024-04-19","cited_by_count":49,"area":null},{"id":"2404.12464","title":"NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models","created":"2024-04-18","cited_by_count":48,"area":null},{"id":"2310.13420","title":"Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations","created":"2023-10-20","cited_by_count":47,"area":null},{"id":"2406.10960","title":"ESCoT: Towards Interpretable Emotional Support Dialogue Systems","created":"2024-06-16","cited_by_count":46,"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":"2403.07230","title":"Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences","created":"2024-03-12","cited_by_count":39,"area":"alignment"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2306.01985","title":"COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements","created":"2023-06-03","cited_by_count":34,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2305.09800","title":"Mirages: On Anthropomorphism in Dialogue Systems","created":"2023-05-16","cited_by_count":30,"area":null},{"id":"2501.17420","title":"Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models","created":"2025-01-29","cited_by_count":30,"area":"agents"},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2412.04036","title":"SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions","created":"2024-12-05","cited_by_count":25,"area":null},{"id":"2305.17701","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","created":"2023-05-28","cited_by_count":24,"area":null},{"id":"2310.14563","title":"NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation","created":"2023-10-23","cited_by_count":24,"area":null},{"id":"2410.21418","title":"Large Language Models for Manufacturing","created":"2024-10-28","cited_by_count":24,"area":null},{"id":"2402.06900","title":"Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric","created":"2024-02-10","cited_by_count":23,"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":"2307.10172","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","created":"2023-07-19","cited_by_count":22,"area":null},{"id":"2311.09799","title":"How Far Can We Extract Diverse Perspectives from Large Language Models?","created":"2023-11-16","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":"2502.11190","title":"ReLearn: Unlearning via Learning for Large Language Models","created":"2025-02-16","cited_by_count":22,"area":"safety"},{"id":"2407.04952","title":"Granular Privacy Control for Geolocation with Vision Language Models","created":"2024-07-06","cited_by_count":21,"area":"mllm"},{"id":"2311.12275","title":"Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesis","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2405.09373","title":"PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models","created":"2024-05-15","cited_by_count":20,"area":null},{"id":"2509.14284","title":"The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration","created":"2025-09-16","cited_by_count":20,"area":"agents"},{"id":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19,"area":null},{"id":"2402.01729","title":"Contextualization Distillation from Large Language Model for Knowledge Graph Completion","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2212.10720","title":"MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions","created":"2022-12-21","cited_by_count":17,"area":null},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2310.15431","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","created":"2023-10-24","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":"2305.14246","title":"Modeling Empathic Similarity in Personal Narratives","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2305.17696","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2504.13211","title":"MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance","created":"2025-04-16","cited_by_count":13,"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":"2304.05253","title":"Approximating Online Human Evaluation of Social Chatbots with Prompting","created":"2023-04-11","cited_by_count":11,"area":null},{"id":"2504.17238","title":"Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues","created":"2025-04-24","cited_by_count":11,"area":"lr"},{"id":"2306.03361","title":"WHAT, WHEN, and HOW to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue","created":"2023-06-06","cited_by_count":10,"area":null},{"id":"2408.09819","title":"CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models","created":"2024-08-19","cited_by_count":10,"area":null},{"id":"2502.17720","title":"Spontaneous Giving and Calculated Greed in Language Models","created":"2025-02-24","cited_by_count":10,"area":"lr"},{"id":"2305.02626","title":"\"Oops, Did I Just Say That?\" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process","created":"2023-05-04","cited_by_count":9,"area":null},{"id":"2309.16804","title":"Curriculum-Driven Edubot: A Framework for Developing Language Learning Chatbots Through Synthesizing Conversational Data","created":"2023-09-28","cited_by_count":9,"area":null},{"id":"2210.12429","title":"Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems","created":"2022-10-22","cited_by_count":8,"area":null},{"id":"2407.03958","title":"Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2410.02503","title":"Mixed-Session Conversation with Egocentric Memory","created":"2024-10-03","cited_by_count":8,"area":null},{"id":"2302.07926","title":"Commonsense Reasoning for Conversational AI: A Survey of the State of the Art","created":"2023-02-15","cited_by_count":7,"area":"lr"},{"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":"2309.10015","title":"SYNDICOM: Improving Conversational Commonsense with Error-Injection and Natural Language Feedback","created":"2023-09-18","cited_by_count":6,"area":"lr"},{"id":"2410.12857","title":"Enterprise Benchmarks for Large Language Model Evaluation","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2502.05651","title":"KMI: A Dataset of Korean Motivational Interviewing Dialogues for Psychotherapy","created":"2025-02-08","cited_by_count":5,"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":"2305.14757","title":"Psychological Metrics for Dialog System Evaluation","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2410.15297","title":"Redefining Proactivity for Information Seeking Dialogue","created":"2024-10-20","cited_by_count":4,"area":null},{"id":"2511.09918","title":"MINDS: A Cross-cultural Dialogue Corpus for Social Norm Classification and Adherence Detection","created":"2025-11-13","cited_by_count":4,"area":"rag"},{"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":"2402.01719","title":"Measuring Moral Inconsistencies in Large Language Models","created":"2024-01-26","cited_by_count":3,"area":null},{"id":"2402.13709","title":"SaGE: Evaluating Moral Consistency in Large Language Models","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2405.10128","title":"Red Teaming Language Models for Processing Contradictory Dialogues","created":"2024-05-16","cited_by_count":3,"area":"safety"},{"id":"2405.15067","title":"Promoting Constructive Deliberation: Reframing for Receptiveness","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2407.05750","title":"Large Language Models Understand Layout","created":"2024-07-08","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":"2410.03870","title":"From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2411.04496","title":"Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model","created":"2024-11-07","cited_by_count":3,"area":"agents"},{"id":"2506.00421","title":"Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2506.01495","title":"C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2402.01736","title":"SADAS: A Dialogue Assistant System Towards Remediating Norm Violations in Bilingual Socio-Cultural Conversations","created":"2024-01-29","cited_by_count":2,"area":null},{"id":"2504.15188","title":"Synergistic Weak-Strong Collaboration by Aligning Preferences","created":"2025-04-21","cited_by_count":2,"area":"lr"},{"id":"2504.17390","title":"PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2509.18395","title":"NormGenesis: Multicultural Dialogue Generation via Exemplar-Guided Social Norm Modeling and Violation Recovery","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2602.04742","title":"Inference-Time Reasoning Selectively Reduces Implicit Social Bias in Large Language Models","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2603.10243","title":"GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"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":"2307.07255","title":"Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems","created":"2023-07-14","cited_by_count":1,"area":"agents"},{"id":"2310.14340","title":"Social Commonsense-Guided Search Query Generation for Open-Domain Knowledge-Powered Conversations","created":"2023-10-22","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":"2410.14194","title":"Speciesism in Natural Language Processing Research","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2505.12741","title":"Language Model Networks: Supervision-Efficient Learning through Dense Communication","created":"2025-05-19","cited_by_count":1,"area":"lr"},{"id":"2506.00195","title":"Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences","created":"2025-05-30","cited_by_count":1,"area":"alignment"},{"id":"2509.13569","title":"Overview of Dialog System Evaluation Track: Dimensionality, Language, Culture and Safety at DSTC 12","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2601.17481","title":"Lattice: Generative Guardrails for Conversational Agents","created":"2026-01-24","cited_by_count":1,"area":"safety"},{"id":"2605.30654","title":"EUDAIMONIA: Evaluating Undesirable Dynamics in AI","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2607.19834","title":"D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarios","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2310.10967","title":"EXMODD: An EXplanatory Multimodal Open-Domain Dialogue dataset","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2402.00143","title":"Making a Long Story Short in Conversation Modeling","created":"2024-01-31","cited_by_count":0,"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":"2505.09923","title":"\"There Is No Such Thing as a Dumb Question,\" But There Are Good Ones","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2506.19483","title":"Commonsense Generation and Evaluation for Dialogue Systems using Large Language Models","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2509.14622","title":"Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection","created":"2025-09-18","cited_by_count":0,"area":"rag"},{"id":"2601.03273","title":"A Multi-Perspective Benchmark and Moderation Model for Evaluating Safety and Adversarial Robustness","created":"2025-12-22","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}