{"total":154,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"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":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244,"area":"synth"},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2308.09662","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","created":"2023-08-18","cited_by_count":223,"area":"safety"},{"id":"2312.17617","title":"Large Language Models for Generative Information Extraction: A Survey","created":"2023-12-29","cited_by_count":185,"area":null},{"id":"2304.01852","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","created":"2023-04-04","cited_by_count":154,"area":null},{"id":"2306.05817","title":"How Can Recommender Systems Benefit from Large Language Models: A Survey","created":"2023-06-09","cited_by_count":142,"area":null},{"id":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"area":null},{"id":"2303.11032","title":"DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4","created":"2023-03-20","cited_by_count":130,"area":null},{"id":"2310.07849","title":"Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations","created":"2023-10-11","cited_by_count":100,"area":"synth"},{"id":"2502.11211","title":"A Survey of LLM-based Agents in Medicine: How far are we from Baymax?","created":"2025-02-16","cited_by_count":85,"area":"agents"},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2502.11357","title":"Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents","created":"2025-02-17","cited_by_count":72,"area":"agents"},{"id":"2308.06374","title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges","created":"2023-08-11","cited_by_count":71,"area":null},{"id":"2312.02913","title":"Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions","created":"2023-12-05","cited_by_count":70,"area":null},{"id":"2305.17256","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","created":"2023-05-26","cited_by_count":69,"area":null},{"id":"2308.09067","title":"Contrasting Linguistic Patterns in Human and LLM-Generated News Text","created":"2023-08-17","cited_by_count":62,"area":null},{"id":"2403.02333","title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","created":"2024-03-04","cited_by_count":58,"area":"lr"},{"id":"2406.00793","title":"Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective","created":"2024-06-02","cited_by_count":57,"area":null},{"id":"2310.11703","title":"A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge","created":"2023-10-18","cited_by_count":55,"area":null},{"id":"2304.05454","title":"Zero-shot Temporal Relation Extraction with ChatGPT","created":"2023-04-11","cited_by_count":53,"area":null},{"id":"2303.13592","title":"Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages","created":"2023-03-23","cited_by_count":51,"area":null},{"id":"2305.14450","title":"An Empirical Study on Information Extraction using Large Language Models","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2406.05688","title":"Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions","created":"2024-06-09","cited_by_count":46,"area":null},{"id":"2405.08603","title":"A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine","created":"2024-05-14","cited_by_count":45,"area":"mllm"},{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2404.14361","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets","created":"2024-04-22","cited_by_count":36,"area":"synth"},{"id":"2403.04190","title":"Generative AI for Synthetic Data Generation: Methods, Challenges and the Future","created":"2024-03-07","cited_by_count":33,"area":"synth"},{"id":"2405.14191","title":"S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models","created":"2024-05-23","cited_by_count":33,"area":null},{"id":"2405.17067","title":"Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization","created":"2024-05-27","cited_by_count":32,"area":null},{"id":"2307.08925","title":"Integration of Large Language Models and Federated Learning","created":"2023-07-18","cited_by_count":31,"area":null},{"id":"2310.06827","title":"Teaching Language Models to Hallucinate Less with Synthetic Tasks","created":"2023-10-10","cited_by_count":31,"area":null},{"id":"2311.01677","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","created":"2023-11-03","cited_by_count":31,"area":null},{"id":"2303.16756","title":"Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching","created":"2023-03-24","cited_by_count":30,"area":null},{"id":"2409.11968","title":"Efficacy of Synthetic Data as a Benchmark","created":"2024-09-18","cited_by_count":30,"area":"synth"},{"id":"2401.02458","title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","created":"2024-01-04","cited_by_count":27,"area":null},{"id":"2311.12410","title":"nach0: Multimodal Natural and Chemical Languages Foundation Model","created":"2023-11-21","cited_by_count":26,"area":null},{"id":"2401.06774","title":"Two Directions for Clinical Data Generation with Large Language Models: Data-to-Label and Label-to-Data","created":"2023-12-09","cited_by_count":26,"area":null},{"id":"2303.07610","title":"Exploring ChatGPT's Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences","created":"2023-03-14","cited_by_count":25,"area":null},{"id":"2409.11423","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","created":"2024-09-12","cited_by_count":22,"area":"synth"},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2311.00287","title":"Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models","created":"2023-11-01","cited_by_count":20,"area":null},{"id":"2402.16041","title":"Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy","created":"2024-02-25","cited_by_count":20,"area":null},{"id":"2405.01886","title":"Aloe: A Family of Fine-tuned Open Healthcare LLMs","created":"2024-05-03","cited_by_count":20,"area":"safety"},{"id":"2310.14088","title":"MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation","created":"2023-10-21","cited_by_count":19,"area":null},{"id":"2408.02056","title":"MedSyn: LLM-based Synthetic Medical Text Generation Framework","created":"2024-08-04","cited_by_count":19,"area":null},{"id":"2412.10136","title":"Can LLMs Convert Graphs to Text-Attributed Graphs?","created":"2024-12-13","cited_by_count":19,"area":null},{"id":"2312.11518","title":"User Modeling in the Era of Large Language Models: Current Research and Future Directions","created":"2023-12-11","cited_by_count":18,"area":null},{"id":"2412.08847","title":"MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation","created":"2024-12-12","cited_by_count":18,"area":null},{"id":"2406.10303","title":"A Survey on Large Language Models from General Purpose to Medical Applications: Datasets, Methodologies, and Evaluations","created":"2024-06-14","cited_by_count":16,"area":null},{"id":"2502.09369","title":"Language Agents as Digital Representatives in Collective Decision-Making","created":"2025-02-13","cited_by_count":16,"area":"agents"},{"id":"2504.21051","title":"Multimodal Large Language Models for Medicine: A Comprehensive Survey","created":"2025-04-29","cited_by_count":16,"area":"mllm"},{"id":"2410.01720","title":"Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective","created":"2024-10-02","cited_by_count":15,"area":"synth"},{"id":"2306.16931","title":"UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?","created":"2023-06-29","cited_by_count":14,"area":null},{"id":"2403.08820","title":"Diet-ODIN: A Novel Framework for Opioid Misuse Detection with Interpretable Dietary Patterns","created":"2024-02-21","cited_by_count":14,"area":null},{"id":"2406.12844","title":"Synergizing Foundation Models and Federated Learning: A Survey","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2311.07715","title":"PolyIE: A Dataset of Information Extraction from Polymer Material Scientific Literature","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2405.00716","title":"Large Language Models in the Clinic: A Comprehensive Benchmark","created":"2024-04-25","cited_by_count":13,"area":null},{"id":"2402.13919","title":"SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","created":"2024-02-21","cited_by_count":12,"area":"alignment"},{"id":"2403.06414","title":"Evolving Knowledge Distillation with Large Language Models and Active Learning","created":"2024-03-11","cited_by_count":12,"area":"distill"},{"id":"2306.08833","title":"Safeguarding Crowdsourcing Surveys from ChatGPT with Prompt Injection","created":"2023-06-15","cited_by_count":11,"area":"safety"},{"id":"2407.12522","title":"Struct-X: Enhancing Large Language Models Reasoning with Structured Data","created":"2024-07-17","cited_by_count":11,"area":"lr"},{"id":"2503.01900","title":"LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2404.04960","title":"PairAug: What Can Augmented Image-Text Pairs Do for Radiology?","created":"2024-04-07","cited_by_count":10,"area":"mllm"},{"id":"2503.16585","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","created":"2025-03-20","cited_by_count":10,"area":"mllm"},{"id":"2411.03250","title":"DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models","created":"2024-11-05","cited_by_count":9,"area":"diffusion"},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2404.14445","title":"A Multi-Faceted Evaluation Framework for Assessing Synthetic Data Generated by Large Language Models","created":"2024-04-20","cited_by_count":8,"area":"synth"},{"id":"2408.15207","title":"Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks","created":"2024-08-27","cited_by_count":8,"area":"safety"},{"id":"2410.22182","title":"Synthetic Data Generation with Large Language Models for Personalized Community Question Answering","created":"2024-10-29","cited_by_count":8,"area":"synth"},{"id":"2504.09277","title":"SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Query Generation for Personalized Tourism Recommenders","created":"2025-04-12","cited_by_count":8,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2402.08073","title":"Grounding Data Science Code Generation with Input-Output Specifications","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2407.10020","title":"Causality extraction from medical text using Large Language Models (LLMs)","created":"2024-07-13","cited_by_count":7,"area":null},{"id":"2407.19568","title":"Are LLMs Good Annotators for Discourse-level Event Relation Extraction?","created":"2024-07-28","cited_by_count":7,"area":null},{"id":"2310.03293","title":"A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's Intentions","created":"2023-10-05","cited_by_count":6,"area":"agents"},{"id":"2311.01751","title":"EmojiLM: Modeling the New Emoji Language","created":"2023-11-03","cited_by_count":6,"area":null},{"id":"2410.13098","title":"A Little Human Data Goes A Long Way","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2310.20033","title":"Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","created":"2023-10-30","cited_by_count":5,"area":"alignment"},{"id":"2409.16563","title":"Enhancing disease detection in radiology reports through fine-tuning lightweight LLM on weak labels","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2412.12981","title":"Unlocking LLMs: Addressing Scarce Data and Bias Challenges in Mental Health","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2501.15108","title":"Knowledge Hierarchy Guided Biological-Medical Dataset Distillation for Domain LLM Training","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2305.11364","title":"Visualizing Linguistic Diversity of Text Datasets Synthesized by Large Language Models","created":"2023-05-19","cited_by_count":4,"area":null},{"id":"2306.02077","title":"Utilizing ChatGPT to Enhance Clinical Trial Enrollment","created":"2023-06-03","cited_by_count":4,"area":null},{"id":"2401.06088","title":"Autocompletion of Chief Complaints in the Electronic Health Records using Large Language Models","created":"2024-01-11","cited_by_count":4,"area":null},{"id":"2402.10597","title":"Efficiency at Scale: Investigating the Performance of Diminutive Language Models in Clinical Tasks","created":"2024-02-16","cited_by_count":4,"area":null},{"id":"2403.16909","title":"Towards Algorithmic Fidelity: Mental Health Representation across Demographics in Synthetic vs. Human-generated Data","created":"2024-03-25","cited_by_count":4,"area":null},{"id":"2502.00808","title":"Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications","created":"2025-02-02","cited_by_count":4,"area":"synth"},{"id":"2502.03323","title":"Out-of-Distribution Detection using Synthetic Data Generation","created":"2025-02-05","cited_by_count":4,"area":"synth"},{"id":"2310.13469","title":"Ask Language Model to Clean Your Noisy Translation Data","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2311.14583","title":"GPT Struct Me: Probing GPT Models on Narrative Entity Extraction","created":"2023-11-24","cited_by_count":3,"area":null},{"id":"2404.09593","title":"Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2405.20787","title":"PGA-SciRE: Harnessing LLM on Data Augmentation for Enhancing Scientific Relation Extraction","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2409.09501","title":"Synthetic4Health: Generating Annotated Synthetic Clinical Letters","created":"2024-09-14","cited_by_count":3,"area":null},{"id":"2409.15868","title":"Privacy Evaluation Benchmarks for NLP Models","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2502.17394","title":"SNaRe: Domain-aware Data Generation for Low-Resource Event Detection","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2507.07852","title":"Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective","created":"2025-07-10","cited_by_count":3,"area":null}],"next_cursor":"100"}