{"list":"other","total":51,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124},{"id":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123},{"id":"2305.13626","title":"Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration","created":"2023-05-23","cited_by_count":116},{"id":"2510.01171","title":"Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity","created":"2025-10-01","cited_by_count":105},{"id":"2403.19154","title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","created":"2024-03-28","cited_by_count":104},{"id":"2311.09469","title":"Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs","created":"2023-11-16","cited_by_count":98},{"id":"2310.11589","title":"Eliciting Human Preferences with Language Models","created":"2023-10-17","cited_by_count":92},{"id":"2410.13788","title":"Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions","created":"2024-10-17","cited_by_count":76},{"id":"2309.14459","title":"Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces","created":"2023-09-25","cited_by_count":72},{"id":"2412.13678","title":"Clio: Privacy-Preserving Insights into Real-World AI Use","created":"2024-12-18","cited_by_count":72},{"id":"2412.11102","title":"Empowering LLMs to Understand and Generate Complex Vector Graphics","created":"2024-12-15","cited_by_count":66},{"id":"2510.06552","title":"Flipping the Dialogue: Training and Evaluating User Language Models","created":"2025-10-08","cited_by_count":58},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57},{"id":"2510.05444","title":"SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?","created":"2025-10-06","cited_by_count":50},{"id":"2506.12469","title":"Levels of Autonomy for AI Agents","created":"2025-06-14","cited_by_count":48},{"id":"2511.02208","title":"Training Proactive and Personalized LLM Agents","created":"2025-11-04","cited_by_count":46},{"id":"2310.14696","title":"Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models","created":"2023-10-23","cited_by_count":43},{"id":"2502.18968","title":"Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles","created":"2025-02-26","cited_by_count":41},{"id":"2503.17126","title":"Modifying Large Language Model Post-Training for Diverse Creative Writing","created":"2025-03-21","cited_by_count":40},{"id":"2310.10996","title":"ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarification","created":"2023-10-17","cited_by_count":38},{"id":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38},{"id":"2403.11164","title":"The Effects of Generative AI on Design Fixation and Divergent Thinking","created":"2024-03-17","cited_by_count":37},{"id":"2504.07114","title":"ChatBench: From Static Benchmarks to Human-AI Evaluation","created":"2025-03-22","cited_by_count":34},{"id":"2306.09821","title":"Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System","created":"2023-06-16","cited_by_count":32},{"id":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30},{"id":"2308.11534","title":"PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator","created":"2023-08-21","cited_by_count":29},{"id":"2311.07434","title":"Understanding Users' Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Level","created":"2023-11-13","cited_by_count":26},{"id":"2405.13028","title":"DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues","created":"2024-05-16","cited_by_count":24},{"id":"2408.04112","title":"Patchview: LLM-Powered Worldbuilding with Generative Dust and Magnet Visualization","created":"2024-08-07","cited_by_count":23},{"id":"2310.09985","title":"Prompting for Discovery: Flexible Sense-Making for AI Art-Making with Dreamsheets","created":"2023-10-15","cited_by_count":22},{"id":"2508.01674","title":"CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions","created":"2025-08-03","cited_by_count":22},{"id":"2104.03702","title":"Media Cloud: Massive Open Source Collection of Global News on the Open Web","created":"2021-04-08","cited_by_count":20},{"id":"2408.13545","title":"IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering","created":"2024-08-24","cited_by_count":19},{"id":"2506.03930","title":"VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation","created":"2025-06-04","cited_by_count":17},{"id":"2502.18736","title":"AI-Instruments: Embodying Prompts as Instruments to Abstract & Reflect Graphical Interface Commands as General-Purpose Tools","created":"2025-02-26","cited_by_count":8},{"id":"2505.21362","title":"Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History","created":"2025-05-27","cited_by_count":5}],"next_cursor":null}