{"total":19,"rows":[{"id":"2506.08584","title":"CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering","created":"2025-06-10","cited_by_count":21,"area":null},{"id":"2502.18316","title":"WiCkeD: A Simple Method to Make Multiple Choice Benchmarks More Challenging","created":"2025-02-25","cited_by_count":11,"area":null},{"id":"2505.11613","title":"MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2506.02921","title":"A Controllable Examination for Long-Context Language Models","created":"2025-06-03","cited_by_count":7,"area":null},{"id":"2601.07506","title":"Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2602.01714","title":"MedAraBench: Large-Scale Arabic Medical Question Answering Dataset and Benchmark","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2505.17682","title":"Tuning Language Models for Robust Prediction of Diverse User Behaviors","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2505.21958","title":"Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.07309","title":"PIE: Performance Interval Estimation for Free-Form Generation Tasks","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2510.10415","title":"CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2602.16039","title":"How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2604.02650","title":"Revealing the Learning Dynamics of Long-Context Continual Pre-training","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2505.18331","title":"PerMedCQA: Benchmarking Large Language Models on Medical Consumer Question Answering in Persian Language","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2507.18143","title":"HIVMedQA: Benchmarking large language models for HIV medical decision support","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2510.18691","title":"Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.01360","title":"Safer in Translation? Presupposition Robustness in Indic Languages","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2602.11924","title":"Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2605.21807","title":"When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.20663","title":"DrugBench: Evaluating AI Control Protocols for Medication Harm Mitigation","created":"2026-06-10","cited_by_count":0,"area":null}],"next_cursor":null}