{"total":22,"rows":[{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163,"area":null},{"id":"2505.24785","title":"EXP-Bench: Can AI Conduct AI Research Experiments?","created":"2025-05-30","cited_by_count":37,"area":null},{"id":"2502.14301","title":"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models","created":"2025-02-20","cited_by_count":19,"area":null},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2311.07387","title":"Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2501.18119","title":"Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models","created":"2025-01-30","cited_by_count":11,"area":null},{"id":"2505.13484","title":"Evaluating Large Language Models for Real-World Engineering Tasks","created":"2025-05-12","cited_by_count":7,"area":null},{"id":"2506.00309","title":"Evaluation of LLMs for mathematical problem solving","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2503.11227","title":"GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction","created":"2025-03-14","cited_by_count":6,"area":null},{"id":"2601.15812","title":"ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models","created":"2026-01-22","cited_by_count":6,"area":null},{"id":"2404.06731","title":"Accuracy of a Large Language Model in Distinguishing Anti- And Pro-vaccination Messages on Social Media: The Case of Human Papillomavirus Vaccination","created":"2024-04-10","cited_by_count":5,"area":null},{"id":"2503.10628","title":"Uncertainty in Action: Confidence Elicitation in Embodied Agents","created":"2025-03-13","cited_by_count":5,"area":null},{"id":"2502.14734","title":"Sentence Smith: Controllable Edits for Evaluating Text Embeddings","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2503.02249","title":"Natural Selection via Foundation Models for Soft Robot Evolution","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2410.14335","title":"Critical Questions Generation: Motivation and Challenges","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2602.22771","title":"ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2605.17435","title":"BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2502.08415","title":"FSLI: An Interpretable Formal Semantic System for One-Dimensional Ordering Inference","created":"2025-02-12","cited_by_count":0,"area":null},{"id":"2505.04535","title":"FDA-Opt: Federated Fine-Tuning via Dynamic Update Schedules","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2604.15800","title":"From Intention to Text: AI-Supported Goal Setting in Academic Writing","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2608.27462","title":"Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}