{"total":45,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246,"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":"2311.04939","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","created":"2023-11-08","cited_by_count":202,"area":null},{"id":"2304.08085","title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","created":"2023-04-17","cited_by_count":170,"area":null},{"id":"2305.16326","title":"Benchmarking large language models for biomedical natural language processing applications and recommendations","created":"2023-05-10","cited_by_count":78,"area":null},{"id":"2303.07992","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","created":"2023-03-14","cited_by_count":71,"area":null},{"id":"2403.02509","title":"SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models","created":"2024-03-04","cited_by_count":56,"area":null},{"id":"2304.03347","title":"Towards Interpretable Mental Health Analysis with Large Language Models","created":"2023-04-06","cited_by_count":53,"area":null},{"id":"2304.07666","title":"ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models","created":"2023-04-16","cited_by_count":42,"area":null},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2305.14976","title":"GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP","created":"2023-05-24","cited_by_count":37,"area":null},{"id":"2305.08714","title":"Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks","created":"2023-05-15","cited_by_count":25,"area":null},{"id":"2310.16379","title":"Evaluating General-Purpose AI with Psychometrics","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2305.13954","title":"Robust Prompt Optimization for Large Language Models Against Distribution Shifts","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2410.07053","title":"Robots in the Middle: Evaluating LLMs in Dispute Resolution","created":"2024-10-09","cited_by_count":14,"area":null},{"id":"2402.14568","title":"LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition","created":"2024-02-22","cited_by_count":11,"area":null},{"id":"2406.11890","title":"Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2312.04642","title":"On Sarcasm Detection with OpenAI GPT-based Models","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2310.17848","title":"Boosting Data Analytics With Synthetic Volume Expansion","created":"2023-10-27","cited_by_count":7,"area":null},{"id":"2509.16596","title":"Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels","created":"2025-09-20","cited_by_count":7,"area":null},{"id":"2412.13626","title":"LIFT: Improving Long Context Understanding Through Long Input Fine-Tuning","created":"2024-12-18","cited_by_count":6,"area":null},{"id":"2309.11361","title":"Knowledge Graph Question Answering for Materials Science (KGQA4MAT): Developing Natural Language Interface for Metal-Organic Frameworks Knowledge Graph (MOF-KG) Using LLM","created":"2023-09-20","cited_by_count":5,"area":null},{"id":"2404.02330","title":"Comparative Study of Domain Driven Terms Extraction Using Large Language Models","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2405.20213","title":"PostDoc: Generating Poster from a Long Multimodal Document Using Deep Submodular Optimization","created":"2024-05-30","cited_by_count":5,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2403.13518","title":"Motion Generation from Fine-grained Textual Descriptions","created":"2024-03-20","cited_by_count":4,"area":null},{"id":"2502.12459","title":"Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2504.16315","title":"SignX: Continuous Sign Recognition in Compact Pose-Rich Latent Space","created":"2025-04-22","cited_by_count":4,"area":null},{"id":"2403.17733","title":"Continual Few-shot Event Detection via Hierarchical Augmentation Networks","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2402.11203","title":"Exploring ChatGPT for Next-generation Information Retrieval: Opportunities and Challenges","created":"2024-02-17","cited_by_count":2,"area":null},{"id":"2402.16431","title":"RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2409.15825","title":"60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2504.08792","title":"Enhancing NER Performance in Low-Resource Pakistani Languages using Cross-Lingual Data Augmentation","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2403.16176","title":"Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals","created":"2024-03-24","cited_by_count":1,"area":null},{"id":"2502.15616","title":"Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2308.02514","title":"Language models as master equation solvers","created":"2023-07-29","cited_by_count":0,"area":null},{"id":"2407.15694","title":"Counter Turing Test ($CT^2$): Investigating AI-Generated Text Detection for Hindi -- Ranking LLMs based on Hindi AI Detectability Index ($ADI_{hi}$)","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2411.00045","title":"A Novel Psychometrics-Based Approach to Developing Professional Competency Benchmark for Large Language Models","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2504.06166","title":"Assessing how hyperparameters impact Large Language Models' sarcasm detection performance","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2512.22738","title":"Harnessing Large Language Models for Biomedical Named Entity Recognition","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2603.17021","title":"Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.19505","title":"Enhancing Unsupervised Keyword Extraction in Academic Papers through Integrating Highlights with Abstract","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.04665","title":"Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2609.18739","title":"A Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}