{"total":30,"rows":[{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2603.03303","title":"HumanLM: Simulating Users with State Alignment Beats Response Imitation","created":"2026-02-07","cited_by_count":37,"area":null},{"id":"2507.23158","title":"User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal","created":"2025-07-30","cited_by_count":19,"area":null},{"id":"2604.17283","title":"HorizonBench: Long-Horizon Personalization with Evolving Preferences","created":"2026-04-19","cited_by_count":17,"area":null},{"id":"2506.21521","title":"Potemkin Understanding in Large Language Models","created":"2025-06-26","cited_by_count":15,"area":null},{"id":"2509.25369","title":"Generative Value Conflicts Reveal LLM Priorities","created":"2025-09-29","cited_by_count":13,"area":null},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2505.06108","title":"LLMs Outperform Experts on Challenging Biology Benchmarks","created":"2025-05-09","cited_by_count":9,"area":null},{"id":"2509.19364","title":"The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behavior","created":"2025-09-18","cited_by_count":8,"area":null},{"id":"2510.18731","title":"Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards","created":"2025-10-21","cited_by_count":6,"area":null},{"id":"2602.03429","title":"DiscoverLLM: From Executing Intents to Discovering Them","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2506.14200","title":"ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2602.11483","title":"Understanding Persuasive Interactions between Generative Social Agents and Humans: The Knowledge-based Persuasion Model (KPM)","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2601.07973","title":"Cultural Compass: A Framework for Organizing Societal Norms to Detect Violations in Human-AI Conversations","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2605.02624","title":"Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations","created":"2026-05-04","cited_by_count":2,"area":null},{"id":"2605.15205","title":"Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2607.10428","title":"Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2608.17150","title":"KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2608.18554","title":"CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2609.21117","title":"From Task Success to Productive Success: Evaluating Human-AI Collaboration by Quality and Cost","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2604.14137","title":"From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2609.08861","title":"API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.12366","title":"ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.14849","title":"LLMs as Oracles: Reliance on LLMs for Subjective Personal Questions","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.16793","title":"Available but Unclaimed: An Empirical Study of Human-AI Synergy","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2610.02460","title":"CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05534","title":"Dataset Signatures in Human-LLM Interactions and User Modeling","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.13617","title":"Training User Simulators with Latent Intrinsic Feedback","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}