{"total":73,"rows":[{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116,"area":"safety"},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109,"area":"agents"},{"id":"2411.16489","title":"O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?","created":"2024-11-25","cited_by_count":92,"area":"lr"},{"id":"2304.10436","title":"Safety Assessment of Chinese Large Language Models","created":"2023-04-20","cited_by_count":85,"area":null},{"id":"2307.09705","title":"CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility","created":"2023-07-19","cited_by_count":85,"area":null},{"id":"2202.13047","title":"AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation","created":"2022-02-26","cited_by_count":79,"area":null},{"id":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76,"area":null},{"id":"2308.16149","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","created":"2023-08-30","cited_by_count":69,"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":"2402.16444","title":"ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors","created":"2024-02-26","cited_by_count":51,"area":null},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48,"area":null},{"id":"2410.23252","title":"Evaluating Cultural and Social Awareness of LLM Web Agents","created":"2024-10-30","cited_by_count":45,"area":"agents"},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42,"area":null},{"id":"2210.10045","title":"SafeText: A Benchmark for Exploring Physical Safety in Language Models","created":"2022-10-18","cited_by_count":41,"area":null},{"id":"2306.03350","title":"Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning","created":"2023-06-06","cited_by_count":41,"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":"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":"2203.09313","title":"EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training","created":"2022-03-17","cited_by_count":31,"area":null},{"id":"2305.09800","title":"Mirages: On Anthropomorphism in Dialogue Systems","created":"2023-05-16","cited_by_count":30,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2509.09660","title":"Steering MoE LLMs via Expert (De)Activation","created":"2025-09-11","cited_by_count":26,"area":"moe"},{"id":"2311.18580","title":"FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity","created":"2023-11-30","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":"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":"2306.13651","title":"Bring Your Own Data! Self-Supervised Evaluation for Large Language Models","created":"2023-06-23","cited_by_count":17,"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":"2203.10012","title":"Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges","created":"2022-03-18","cited_by_count":13,"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":"2310.09624","title":"ASSERT: Automated Safety Scenario Red Teaming for Evaluating the Robustness of Large Language Models","created":"2023-10-14","cited_by_count":12,"area":"safety"},{"id":"2210.00572","title":"Risk-graded Safety for Handling Medical Queries in Conversational AI","created":"2022-10-02","cited_by_count":11,"area":null},{"id":"2210.10329","title":"Language Detoxification with Attribute-Discriminative Latent Space","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2412.06483","title":"SafeWorld: Geo-Diverse Safety Alignment","created":"2024-12-09","cited_by_count":11,"area":"wm"},{"id":"2408.10902","title":"Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs","created":"2024-08-20","cited_by_count":10,"area":null},{"id":"2410.11114","title":"Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios","created":"2024-10-14","cited_by_count":10,"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":"2212.09180","title":"Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems","created":"2022-12-18","cited_by_count":9,"area":null},{"id":"2506.06636","title":"SafeLawBench: Towards Safe Alignment of Large Language Models","created":"2025-06-07","cited_by_count":9,"area":"alignment"},{"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":"2212.01810","title":"Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation","created":"2022-12-04","cited_by_count":8,"area":null},{"id":"2403.00862","title":"NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism","created":"2024-02-29","cited_by_count":8,"area":null},{"id":"2410.14141","title":"Coherence-Driven Multimodal Safety Dialogue with Active Learning for Embodied Agents","created":"2024-10-18","cited_by_count":8,"area":"agents"},{"id":"2212.01700","title":"Towards Robust NLG Bias Evaluation with Syntactically-diverse Prompts","created":"2022-12-03","cited_by_count":7,"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":"2408.01452","title":"Building a Domain-specific Guardrail Model in Production","created":"2024-07-24","cited_by_count":6,"area":"safety"},{"id":"2409.01247","title":"Conversational Complexity for Assessing Risk in Large Language Models","created":"2024-09-02","cited_by_count":6,"area":"safety"},{"id":"2212.09667","title":"Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2409.02718","title":"\"Yes, My LoRD.\" Guiding Language Model Extraction with Locality Reinforced Distillation","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2412.11250","title":"Beyond Discrete Personas: Personality Modeling Through Journal Intensive Conversations","created":"2024-12-15","cited_by_count":5,"area":null},{"id":"2510.08646","title":"Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy","created":"2025-10-09","cited_by_count":5,"area":"alignment"},{"id":"2410.23902","title":"Responsible Retrieval Augmented Generation for Climate Decision Making from Documents","created":"2024-10-31","cited_by_count":4,"area":"rag"},{"id":"2509.25271","title":"RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2308.06507","title":"AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models","created":"2023-08-12","cited_by_count":3,"area":null},{"id":"2308.14641","title":"Challenges of GPT-3-based Conversational Agents for Healthcare","created":"2023-08-28","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":"2407.17075","title":"SAFETY-J: Evaluating Safety with Critique","created":"2024-07-24","cited_by_count":3,"area":null},{"id":"2409.15766","title":"CHBench: A Chinese Dataset for Evaluating Health in Large Language Models","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2601.03699","title":"RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2501.00697","title":"PANDA -- Paired Anti-hate Narratives Dataset from Asia: Using an LLM-as-a-Judge to Create the First Chinese Counterspeech Dataset","created":"2025-01-01","cited_by_count":2,"area":null},{"id":"2501.06137","title":"Supervision policies can shape long-term risk management in general-purpose AI models","created":"2025-01-10","cited_by_count":2,"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":"2310.16119","title":"Alquist 5.0: Dialogue Trees Meet Generative Models. A Novel Approach for Enhancing SocialBot Conversations","created":"2023-10-24","cited_by_count":1,"area":null},{"id":"2505.18426","title":"Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps","created":"2025-05-23","cited_by_count":1,"area":"rag"},{"id":"2512.06193","title":"Do You Feel Comfortable? Detecting Hidden Conversational Escalation in AI Chatbots","created":"2025-12-05","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":"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":"2404.08666","title":"Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences","created":"2024-03-31","cited_by_count":0,"area":null},{"id":"2510.12217","title":"HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2602.15835","title":"A Methodology for Identifying Evaluation Items for Practical Dialogue Systems Based on Business-Dialogue System Alignment Models","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2604.17301","title":"RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.23974","title":"AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue","created":"2026-05-13","cited_by_count":0,"area":null}],"next_cursor":null}