{"list":"other","total":51,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2402.10373","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","created":"2024-02-15","cited_by_count":301},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2301.13808","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","created":"2023-01-31","cited_by_count":178},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2311.08718","title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","created":"2023-11-15","cited_by_count":114},{"id":"2309.13567","title":"MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models","created":"2023-09-24","cited_by_count":63},{"id":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61},{"id":"2209.03942","title":"Data Feedback Loops: Model-driven Amplification of Dataset Biases","created":"2022-09-08","cited_by_count":60},{"id":"2407.15847","title":"LLMmap: Fingerprinting For Large Language Models","created":"2024-07-22","cited_by_count":58},{"id":"2206.10883","title":"Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple Granularities","created":"2022-06-22","cited_by_count":47},{"id":"2402.11137","title":"TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks","created":"2024-02-17","cited_by_count":47},{"id":"2408.08946","title":"Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges","created":"2024-08-16","cited_by_count":47},{"id":"2308.07610","title":"Interpretable Online Log Analysis Using Large Language Models with Prompt Strategies","created":"2023-08-15","cited_by_count":38},{"id":"2404.18443","title":"BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers","created":"2024-04-29","cited_by_count":38},{"id":"2401.13169","title":"ReposVul: A Repository-Level High-Quality Vulnerability Dataset","created":"2024-01-24","cited_by_count":36},{"id":"2504.07096","title":"OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens","created":"2025-04-09","cited_by_count":27},{"id":"2207.14529","title":"The Effects of Data Quality on Machine Learning Performance on Tabular Data","created":"2022-07-29","cited_by_count":19},{"id":"2501.03282","title":"From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence","created":"2025-01-05","cited_by_count":18},{"id":"2402.08922","title":"The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes","created":"2024-02-14","cited_by_count":16},{"id":"2405.02178","title":"Assessing and Verifying Task Utility in LLM-Powered Applications","created":"2024-05-03","cited_by_count":16},{"id":"2502.12340","title":"Understanding Silent Data Corruption in LLM Training","created":"2025-02-17","cited_by_count":15},{"id":"2308.12415","title":"Benchmarking Causal Study to Interpret Large Language Models for Source Code","created":"2023-08-23","cited_by_count":14},{"id":"2410.13298","title":"Advancing Large Language Model Attribution through Self-Improving","created":"2024-10-17","cited_by_count":14},{"id":"2501.11041","title":"Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach","created":"2025-01-19","cited_by_count":14},{"id":"2005.06139","title":"Towards Interpretable Deep Learning Models for Knowledge Tracing","created":"2020-05-13","cited_by_count":13},{"id":"2405.19186","title":"MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification","created":"2024-05-29","cited_by_count":13},{"id":"2304.05973","title":"HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting","created":"2023-04-12","cited_by_count":11},{"id":"2402.05512","title":"GPTs Are Multilingual Annotators for Sequence Generation Tasks","created":"2024-02-08","cited_by_count":11},{"id":"2111.02574","title":"Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues","created":"2021-11-04","cited_by_count":10},{"id":"2408.06273","title":"FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data","created":"2024-08-12","cited_by_count":10},{"id":"2305.11527","title":"InstructIE: A Bilingual Instruction-based Information Extraction Dataset","created":"2023-05-19","cited_by_count":9},{"id":"2501.09645","title":"CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding","created":"2025-01-16","cited_by_count":9},{"id":"2306.14397","title":"Discriminating Human-authored from ChatGPT-Generated Code Via Discernable Feature Analysis","created":"2023-06-26","cited_by_count":7},{"id":"2406.11823","title":"On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning","created":"2024-06-17","cited_by_count":7},{"id":"2412.10267","title":"Does Multiple Choice Have a Future in the Age of Generative AI? A Posttest-only RCT","created":"2024-12-13","cited_by_count":7},{"id":"2402.16358","title":"An Integrated Data Processing Framework for Pretraining Foundation Models","created":"2024-02-26","cited_by_count":6},{"id":"2405.01121","title":"Efficient Data Generation for Source-grounded Information-seeking Dialogs: A Use Case for Meeting Transcripts","created":"2024-05-02","cited_by_count":6},{"id":"1806.00910","title":"An unsupervised and customizable misspelling generator for mining noisy health-related text sources","created":"2018-06-04","cited_by_count":5},{"id":"2312.10057","title":"Generative AI in Writing Research Papers: A New Type of Algorithmic Bias and Uncertainty in Scholarly Work","created":"2023-12-04","cited_by_count":5},{"id":"2510.10161","title":"Large Language Model Sourcing: A Survey","created":"2025-10-11","cited_by_count":5},{"id":"2412.02588","title":"Explainable CTR Prediction via LLM Reasoning","created":"2024-12-03","cited_by_count":4},{"id":"2301.04234","title":"Studying Logging Practice in Machine Learning-based Applications","created":"2023-01-10","cited_by_count":3},{"id":"2411.01353","title":"Can Large Language Model Predict Employee Attrition?","created":"2024-11-02","cited_by_count":3},{"id":"2310.04994","title":"Distantly-Supervised Joint Extraction with Noise-Robust Learning","created":"2023-10-08","cited_by_count":2},{"id":"2401.12990","title":"Topic Modelling: Going Beyond Token Outputs","created":"2024-01-16","cited_by_count":1},{"id":"2407.13909","title":"PRAGyan -- Connecting the Dots in Tweets","created":"2024-07-18","cited_by_count":1}],"next_cursor":null}