{"total":56,"rows":[{"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":"2212.10465","title":"SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization","created":"2022-12-20","cited_by_count":168,"area":null},{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162,"area":null},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109,"area":"agents"},{"id":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76,"area":null},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73,"area":null},{"id":"2202.04173","title":"Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models","created":"2022-02-08","cited_by_count":68,"area":null},{"id":"2203.13299","title":"Mix and Match: Learning-free Controllable Text Generation using Energy Language Models","created":"2022-03-24","cited_by_count":66,"area":null},{"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":"2305.12434","title":"BiasAsker: Measuring the Bias in Conversational AI System","created":"2023-05-21","cited_by_count":53,"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":"2405.05378","title":"\"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations","created":"2024-05-08","cited_by_count":25,"area":null},{"id":"2205.02392","title":"Robust Conversational Agents against Imperceptible Toxicity Triggers","created":"2022-05-05","cited_by_count":23,"area":"agents"},{"id":"2405.16584","title":"MentalManip: A Dataset For Fine-grained Analysis of Mental Manipulation in Conversations","created":"2024-05-26","cited_by_count":21,"area":null},{"id":"2407.04952","title":"Granular Privacy Control for Geolocation with Vision Language Models","created":"2024-07-06","cited_by_count":21,"area":"mllm"},{"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":"2305.14718","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models","created":"2023-05-24","cited_by_count":17,"area":"alignment"},{"id":"2302.09852","title":"Unsupervised Layer-wise Score Aggregation for Textual OOD Detection","created":"2023-02-20","cited_by_count":15,"area":null},{"id":"2307.16457","title":"A Benchmark for Understanding Dialogue Safety in Mental Health Support","created":"2023-07-31","cited_by_count":13,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","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":"2203.17090","title":"PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2205.09314","title":"Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2210.15954","title":"Stanceosaurus: Classifying Stance Towards Multilingual Misinformation","created":"2022-10-28","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":"2305.17280","title":"Improved Instruction Ordering in Recipe-Grounded Conversation","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2312.04510","title":"A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2405.08562","title":"The Unseen Targets of Hate -- A Systematic Review of Hateful Communication Datasets","created":"2024-05-14","cited_by_count":6,"area":null},{"id":"2406.14023","title":"Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2407.01850","title":"Purple-teaming LLMs with Adversarial Defender Training","created":"2024-07-01","cited_by_count":6,"area":"safety"},{"id":"2505.12727","title":"What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2304.12810","title":"Transcending the \"Male Code\": Implicit Masculine Biases in NLP Contexts","created":"2023-04-22","cited_by_count":5,"area":null},{"id":"2310.14804","title":"Large Language Models can Share Images, Too!","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2412.02415","title":"Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2510.10998","title":"ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios","created":"2025-10-13","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":"2212.10557","title":"DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines","created":"2022-12-20","cited_by_count":4,"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":"2505.18927","title":"Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2402.03642","title":"Stanceosaurus 2.0: Classifying Stance Towards Russian and Spanish Misinformation","created":"2024-02-06","cited_by_count":2,"area":null},{"id":"2506.11919","title":"Effectiveness of Counter-Speech against Abusive Content: A Multidimensional Annotation and Classification Study","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2609.19072","title":"Safety-Flag: A Unified Benchmark for the Reliability and Calibration of LLM Content Moderators","created":"2026-08-06","cited_by_count":2,"area":null},{"id":"2111.13833","title":"Partner Personas Generation for Diverse Dialogue Generation","created":"2021-11-27","cited_by_count":1,"area":null},{"id":"2301.10368","title":"Language Model Detoxification in Dialogue with Contextualized Stance Control","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2305.13833","title":"Reducing Sensitivity on Speaker Names for Text Generation from Dialogues","created":"2023-05-23","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":"2412.14008","title":"FarExStance: Explainable Stance Detection for Farsi","created":"2024-12-18","cited_by_count":1,"area":null},{"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":"2608.04415","title":"Social Pressure Breaks Majority Voting in LLM Safety Panels","created":"2026-08-05","cited_by_count":1,"area":"safety"},{"id":"2310.10967","title":"EXMODD: An EXplanatory Multimodal Open-Domain Dialogue dataset","created":"2023-10-17","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":"2410.13313","title":"Mitigating Biases to Embrace Diversity: A Comprehensive Annotation Benchmark for Toxic Language","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2505.16081","title":"BiasLab: Toward Explainable Political Bias Detection with Dual-Axis Annotations and Rationale Indicators","created":"2025-05-21","cited_by_count":0,"area":null},{"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":null}