{"total":111,"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":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"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":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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},{"id":"2303.10794","title":"PheME: A deep ensemble framework for improving phenotype prediction from multi-modal data","created":"2023-03-19","cited_by_count":2,"area":null},{"id":"2311.02205","title":"An Introduction to Natural Language Processing Techniques and Framework for Clinical Implementation in Radiation Oncology","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2401.05200","title":"Knowledge Sharing in Manufacturing using Large Language Models: User Evaluation and Model Benchmarking","created":"2024-01-10","cited_by_count":2,"area":null},{"id":"2402.07645","title":"Detecting the Clinical Features of Difficult-to-Treat Depression using Synthetic Data from Large Language Models","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2403.19511","title":"Improving Clinical NLP Performance through Language Model-Generated Synthetic Clinical Data","created":"2024-03-28","cited_by_count":2,"area":null},{"id":"2406.11455","title":"Adaptive Reinforcement Learning Planning: Harnessing Large Language Models for Complex Information Extraction","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2411.18940","title":"Rephrasing Electronic Health Records for Pretraining Clinical Language Models","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2503.23886","title":"Text2Schema: Filling the Gap in Designing Database Table Structures based on Natural Language","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2509.00647","title":"LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement","created":"2025-08-31","cited_by_count":2,"area":null},{"id":"2509.19770","title":"EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2509.26302","title":"QUARTZ : QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarization","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2403.00260","title":"Extracting Polymer Nanocomposite Samples from Full-Length Documents","created":"2024-03-01","cited_by_count":1,"area":null},{"id":"2403.11103","title":"ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models","created":"2024-03-17","cited_by_count":1,"area":null},{"id":"2403.19802","title":"Developing Healthcare Language Model Embedding Spaces","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2408.13501","title":"Utilizing Large Language Models for Named Entity Recognition in Traditional Chinese Medicine against COVID-19 Literature: Comparative Study","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2412.09859","title":"Financial Sentiment Analysis: Leveraging Actual and Synthetic Data for Supervised Fine-tuning","created":"2024-12-13","cited_by_count":1,"area":null},{"id":"2505.03025","title":"A Typology of Synthetic Datasets for Dialogue Processing in Clinical Contexts","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2602.04785","title":"Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generation","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.16571","title":"Utility-Preserving De-Identification for Math Tutoring: Investigating Numeric Ambiguity in the MathEd-PII Benchmark Dataset","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.00355","title":"StethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical Tasks","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2604.26048","title":"BioGraphletQA: Knowledge-Anchored Generation of Complex QA Datasets","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2308.16615","title":"High Accuracy Location Information Extraction from Social Network Texts Using Natural Language Processing","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2312.17475","title":"EHR Interaction Between Patients and AI: NoteAid EHR Interaction","created":"2023-12-29","cited_by_count":0,"area":null},{"id":"2401.07190","title":"Inroads to a Structured Data Natural Language Bijection and the role of LLM annotation","created":"2024-01-14","cited_by_count":0,"area":null},{"id":"2407.02719","title":"Boosting Biomedical Concept Extraction by Rule-Based Data Augmentation","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2409.00347","title":"Chatting Up Attachment: Using LLMs to Predict Adult Bonds","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2409.15188","title":"PALLM: Evaluating and Enhancing PALLiative Care Conversations with Large Language Models","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2411.19689","title":"MIMDE: Exploring the Use of Synthetic vs Human Data for Evaluating Multi-Insight Multi-Document Extraction Tasks","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2502.16022","title":"Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation: A Comparative Study","created":"2025-02-22","cited_by_count":0,"area":null},{"id":"2503.01266","title":"Voice Cloning for Dysarthric Speech Synthesis: Addressing Data Scarcity in Speech-Language Pathology","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2508.01869","title":"ProKG-Dial: Progressive Multi-Turn Dialogue Construction with Domain Knowledge Graphs","created":"2025-08-03","cited_by_count":0,"area":null}],"next_cursor":"100"}