{"total":115,"rows":[{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265,"area":"lr"},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2309.16289","title":"LawBench: Benchmarking Legal Knowledge of Large Language Models","created":"2023-09-28","cited_by_count":117,"area":null},{"id":"2406.10833","title":"A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery","created":"2024-06-16","cited_by_count":96,"area":null},{"id":"2311.09774","title":"HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs","created":"2023-11-16","cited_by_count":92,"area":null},{"id":"2308.14346","title":"DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation","created":"2023-08-28","cited_by_count":90,"area":null},{"id":"2503.11733","title":"LLM Agents for Education: Advances and Applications","created":"2025-03-14","cited_by_count":59,"area":"agents"},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2403.03640","title":"Apollo: A Lightweight Multilingual Medical LLM towards Democratizing Medical AI to 6B People","created":"2024-03-06","cited_by_count":38,"area":null},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"id":"2411.06469","title":"ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?","created":"2024-11-10","cited_by_count":32,"area":null},{"id":"2406.13890","title":"ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World","created":"2024-06-19","cited_by_count":28,"area":null},{"id":"2408.09199","title":"TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systems","created":"2024-08-17","cited_by_count":28,"area":"rag"},{"id":"2504.15909","title":"Synergizing RAG and Reasoning: A Systematic Review","created":"2025-04-22","cited_by_count":27,"area":"lr"},{"id":"2407.05721","title":"PsycoLLM: Enhancing LLM for Psychological Understanding and Evaluation","created":"2024-07-08","cited_by_count":26,"area":null},{"id":"2312.15883","title":"HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses","created":"2023-12-26","cited_by_count":25,"area":"rag"},{"id":"2409.01790","title":"Training on the Benchmark Is Not All You Need","created":"2024-09-03","cited_by_count":25,"area":null},{"id":"2407.10990","title":"MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models","created":"2024-06-24","cited_by_count":21,"area":null},{"id":"2505.14107","title":"DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models","created":"2025-05-20","cited_by_count":21,"area":"lr"},{"id":"2408.03297","title":"KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models","created":"2024-08-06","cited_by_count":20,"area":"rag"},{"id":"2501.09213","title":"FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training","created":"2025-01-16","cited_by_count":19,"area":"lr"},{"id":"2309.04175","title":"Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese","created":"2023-09-08","cited_by_count":18,"area":null},{"id":"2409.13989","title":"ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models","created":"2024-09-21","cited_by_count":18,"area":null},{"id":"2404.15777","title":"A Comprehensive Survey on Evaluating Large Language Model Applications in the Medical Industry","created":"2024-04-24","cited_by_count":17,"area":null},{"id":"2410.10626","title":"Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts","created":"2024-10-14","cited_by_count":17,"area":"moe"},{"id":"2412.01605","title":"Medchain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence","created":"2024-12-02","cited_by_count":17,"area":"agents"},{"id":"2406.14326","title":"medIKAL: Integrating Knowledge Graphs as Assistants of LLMs for Enhanced Clinical Diagnosis on EMRs","created":"2024-06-20","cited_by_count":16,"area":null},{"id":"2503.13503","title":"SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models","created":"2025-03-12","cited_by_count":15,"area":null},{"id":"2401.15927","title":"E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models","created":"2024-01-29","cited_by_count":13,"area":null},{"id":"2405.15638","title":"M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models","created":"2024-05-24","cited_by_count":13,"area":"lr"},{"id":"2501.02460","title":"Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications","created":"2025-01-05","cited_by_count":13,"area":"rag"},{"id":"2508.13514","title":"ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs","created":"2025-08-19","cited_by_count":13,"area":null},{"id":"2411.11027","title":"BianCang: A Traditional Chinese Medicine Large Language Model","created":"2024-11-17","cited_by_count":12,"area":null},{"id":"2602.10367","title":"LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation","created":"2026-02-10","cited_by_count":12,"area":null},{"id":"2508.16347","title":"Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs","created":"2025-08-22","cited_by_count":11,"area":"lr"},{"id":"2503.13205","title":"MAP: Evaluation and Multi-Agent Enhancement of Large Language Models for Inpatient Pathways","created":"2025-03-17","cited_by_count":10,"area":"agents"},{"id":"2410.03502","title":"CliMedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models in Clinical Scenarios","created":"2024-10-04","cited_by_count":9,"area":null},{"id":"2410.20050","title":"AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels","created":"2024-10-26","cited_by_count":8,"area":null},{"id":"2504.07724","title":"The Multi-Round Diagnostic RAG Framework for Emulating Clinical Reasoning","created":"2025-04-10","cited_by_count":8,"area":"lr"},{"id":"2601.22964","title":"EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2404.09027","title":"MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts","created":"2024-04-13","cited_by_count":7,"area":"moe"},{"id":"2512.24181","title":"MedKGI: Iterative Differential Diagnosis with Medical Knowledge Graphs and Information-Guided Inquiring","created":"2025-12-30","cited_by_count":7,"area":null},{"id":"2410.09699","title":"Honest AI: Fine-Tuning \"Small\" Language Models to Say \"I Don't Know\", and Reducing Hallucination in RAG","created":"2024-10-13","cited_by_count":6,"area":"rag"},{"id":"2503.02359","title":"Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy Paradigm","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2310.07637","title":"OpsEval: A Comprehensive IT Operations Benchmark Suite for Large Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2405.10630","title":"Medical Dialogue: A Survey of Categories, Methods, Evaluation and Challenges","created":"2024-05-17","cited_by_count":5,"area":null},{"id":"2406.04941","title":"TCMD: A Traditional Chinese Medicine QA Dataset for Evaluating Large Language Models","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2406.18034","title":"LLMs for Doctors: Leveraging Medical LLMs to Assist Doctors, Not Replace Them","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2412.06287","title":"PediaBench: A Comprehensive Chinese Pediatric Dataset for Benchmarking Large Language Models","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2505.24063","title":"TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2506.20274","title":"Enterprise Large Language Model Evaluation Benchmark","created":"2025-06-25","cited_by_count":5,"area":null},{"id":"2510.10071","title":"ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2406.12182","title":"Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models","created":"2024-06-18","cited_by_count":4,"area":"alignment"},{"id":"2406.17484","title":"MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2407.11536","title":"Fine-Tuning Medical Language Models for Enhanced Long-Contextual Understanding and Domain Expertise","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2502.18424","title":"Compressing Language Models for Specialized Domains","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2506.01252","title":"MTCMB: A Multi-Task Benchmark Framework for Evaluating LLMs on Knowledge, Reasoning, and Safety in Traditional Chinese Medicine","created":"2025-06-02","cited_by_count":4,"area":"lr"},{"id":"2511.10067","title":"Enhancing the Medical Context-Awareness Ability of LLMs via Multifaceted Self-Refinement Learning","created":"2025-11-13","cited_by_count":4,"area":null},{"id":"2601.16503","title":"MRAG: Benchmarking Retrieval-Augmented Generation for Bio-medicine","created":"2026-01-23","cited_by_count":4,"area":"rag"},{"id":"2409.11783","title":"Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources","created":"2024-09-18","cited_by_count":3,"area":"lr"},{"id":"2410.10901","title":"3DS: Medical Domain Adaptation of LLMs via Decomposed Difficulty-based Data Selection","created":"2024-10-13","cited_by_count":3,"area":null},{"id":"2503.17599","title":"Evaluating Clinical Competencies of Large Language Models with a General Practice Benchmark","created":"2025-03-22","cited_by_count":3,"area":null},{"id":"2505.24826","title":"LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Text","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2506.08349","title":"Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2507.21773","title":"AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2601.19773","title":"Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2402.07234","title":"CPSDBench: A Large Language Model Evaluation Benchmark and Baseline for Chinese Public Security Domain","created":"2024-02-11","cited_by_count":2,"area":null},{"id":"2405.10212","title":"CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2406.11328","title":"Are Large Language Models True Healthcare Jacks-of-All-Trades? Benchmarking Across Health Professions Beyond Physician Exams","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2406.11681","title":"R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models","created":"2024-06-17","cited_by_count":2,"area":"rag"},{"id":"2409.13191","title":"Diabetica: Adapting Large Language Model to Enhance Multiple Medical Tasks in Diabetes Care and Management","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2503.22115","title":"Beyond Single-Sentence Prompts: Upgrading Value Alignment Benchmarks with Dialogues and Stories","created":"2025-03-28","cited_by_count":2,"area":"alignment"},{"id":"2508.09460","title":"Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation","created":"2025-08-13","cited_by_count":2,"area":"lr"},{"id":"2510.13734","title":"GAPS: A Clinically Grounded, Automated Benchmark for Evaluating AI Clinicians","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2511.04328","title":"RxSafeBench: Identifying Medication Safety Issues of Large Language Models in Simulated Consultation","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2512.13297","title":"MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2605.30637","title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2407.19705","title":"CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare","created":"2024-07-29","cited_by_count":1,"area":null},{"id":"2410.04112","title":"Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment","created":"2024-10-05","cited_by_count":1,"area":"alignment"},{"id":"2502.01243","title":"OphthBench: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Ophthalmology","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2502.20988","title":"Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2504.02404","title":"AnesSuite: A Comprehensive Benchmark and Dataset Suite for Anesthesiology Reasoning in LLMs","created":"2025-04-03","cited_by_count":1,"area":"lr"},{"id":"2504.03786","title":"Do \"New Snow Tablets\" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2506.00095","title":"ClinBench-HPB: A Clinical Benchmark for Evaluating LLMs in Hepato-Pancreato-Biliary Diseases","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2509.01354","title":"DPF-CM: A Data Processing Framework with Privacy-Preserving Vector Databases for Chinese Medical LLMs Training and Deployment","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2602.01779","title":"LingLanMiDian: Systematic Evaluation of LLMs on TCM Knowledge and Clinical Reasoning","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.18351","title":"Validating Political Position Predictions of Arguments","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2604.12138","title":"Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions","created":"2026-04-13","cited_by_count":1,"area":"rag"},{"id":"2403.04261","title":"Advancing Chinese biomedical text mining with community challenges","created":"2024-03-07","cited_by_count":0,"area":null},{"id":"2502.14614","title":"ICA-RAG: Information Completeness Guided Adaptive Retrieval-Augmented Generation for Disease Diagnosis","created":"2025-02-20","cited_by_count":0,"area":"rag"},{"id":"2502.20854","title":"A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generation","created":"2025-02-28","cited_by_count":0,"area":"rag"},{"id":"2503.08292","title":"Do LLMs Triage Like Clinicians? A Dynamic Study of Outpatient Referral","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2507.15275","title":"ChiMed 2.0: Advancing Chinese Medical Dataset in Facilitating Large Language Modeling","created":"2025-07-21","cited_by_count":0,"area":"alignment"},{"id":"2508.08270","title":"Doctor Sun: A Bilingual Multimodal Large Language Model for Biomedical AI","created":"2025-07-30","cited_by_count":0,"area":"mllm"},{"id":"2508.20014","title":"CataractSurg-80K: Knowledge-Driven Benchmarking for Structured Reasoning in Ophthalmic Surgery Planning","created":"2025-08-27","cited_by_count":0,"area":"lr"},{"id":"2509.14269","title":"SparseDoctor: Towards Efficient Chat Doctor with Mixture of Experts Enhanced Large Language Models","created":"2025-09-15","cited_by_count":0,"area":"moe"},{"id":"2509.26242","title":"Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing","created":"2025-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}