{"total":17,"rows":[{"id":"2510.06552","title":"Flipping the Dialogue: Training and Evaluating User Language Models","created":"2025-10-08","cited_by_count":58,"area":null},{"id":"2501.08579","title":"LLM-based Human Simulations Have Not Yet Been Reliable","created":"2025-01-15","cited_by_count":30,"area":null},{"id":"2410.23426","title":"Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?","created":"2024-10-30","cited_by_count":26,"area":null},{"id":"2508.06950","title":"Large Language Models Do Not Simulate Human Psychology","created":"2025-08-09","cited_by_count":19,"area":null},{"id":"2405.08035","title":"A LLM-based Controllable, Scalable, Human-Involved User Simulator Framework for Conversational Recommender Systems","created":"2024-05-13","cited_by_count":13,"area":null},{"id":"2602.16938","title":"ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders","created":"2026-02-18","cited_by_count":12,"area":null},{"id":"2502.05556","title":"Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis","created":"2025-02-08","cited_by_count":10,"area":null},{"id":"2511.03508","title":"One Battle After Another: Probing LLMs' Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework","created":"2025-11-05","cited_by_count":9,"area":null},{"id":"2404.00712","title":"Survey of Computerized Adaptive Testing: A Machine Learning Perspective","created":"2024-03-31","cited_by_count":6,"area":null},{"id":"2608.01204","title":"ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2506.03032","title":"TestAgent: An Adaptive and Intelligent Expert for Human Assessment","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2509.20381","title":"USB-Rec: An Effective Framework for Improving Conversational Recommendation Capability of Large Language Model","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2603.18573","title":"Interplay: Training Independent Simulators for Reference-Free Conversational Recommendation","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2605.29711","title":"Personalized Turn-Level User Conversation Satisfaction Benchmark","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.30863","title":"Beyond expert users: agents should help users construct preferences, not just elicit them","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.00010","title":"Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2610.18308","title":"SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}