{"total":22,"rows":[{"id":"2505.08775","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","created":"2025-05-13","cited_by_count":429,"area":null},{"id":"2305.18365","title":"What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks","created":"2023-05-27","cited_by_count":185,"area":null},{"id":"2305.18248","title":"Do Language Models Know When They're Hallucinating References?","created":"2023-05-29","cited_by_count":116,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2309.06794","title":"Cognitive Mirage: A Review of Hallucinations in Large Language Models","created":"2023-09-13","cited_by_count":84,"area":null},{"id":"2401.00820","title":"A Computational Framework for Behavioral Assessment of LLM Therapists","created":"2024-01-01","cited_by_count":62,"area":null},{"id":"2309.00237","title":"Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes","created":"2023-09-01","cited_by_count":51,"area":null},{"id":"2310.10632","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","created":"2023-10-16","cited_by_count":43,"area":null},{"id":"2402.06853","title":"History, Development, and Principles of Large Language Models-An Introductory Survey","created":"2024-02-10","cited_by_count":30,"area":null},{"id":"2402.02008","title":"How well do LLMs cite relevant medical references? An evaluation framework and analyses","created":"2024-02-03","cited_by_count":21,"area":null},{"id":"2410.05180","title":"Mitigating the Risk of Health Inequity Exacerbated by Large Language Models","created":"2024-10-07","cited_by_count":21,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2401.11505","title":"CheX-GPT: Harnessing Large Language Models for Enhanced Chest X-ray Report Labeling","created":"2024-01-21","cited_by_count":10,"area":null},{"id":"2311.08117","title":"Insights into Classifying and Mitigating LLMs' Hallucinations","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2402.02656","title":"RACER: An LLM-powered Methodology for Scalable Analysis of Semi-structured Mental Health Interviews","created":"2024-02-05","cited_by_count":6,"area":null},{"id":"2309.05475","title":"Zero-shot Learning with Minimum Instruction to Extract Social Determinants and Family History from Clinical Notes using GPT Model","created":"2023-09-11","cited_by_count":5,"area":null},{"id":"2404.13307","title":"Beyond Accuracy: Investigating Error Types in GPT-4 Responses to USMLE Questions","created":"2024-04-20","cited_by_count":5,"area":null},{"id":"2310.20153","title":"Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2601.12661","title":"MedConsultBench: A Full-Cycle, Fine-Grained, Process-Aware Benchmark for Medical Consultation Agents","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2407.00541","title":"Answering real-world clinical questions using large language model based systems","created":"2024-06-29","cited_by_count":3,"area":null},{"id":"2408.11866","title":"Crossing New Frontiers: Knowledge-Augmented Large Language Model Prompting for Zero-Shot Text-Based De Novo Molecule Design","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2405.16588","title":"Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games","created":"2024-05-26","cited_by_count":1,"area":null}],"next_cursor":null}