{"list":"other","total":58,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"1812.10464","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","created":"2018-12-26","cited_by_count":434},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300},{"id":"1907.05019","title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","created":"2019-07-11","cited_by_count":257},{"id":"2005.09093","title":"Are All Languages Created Equal in Multilingual BERT?","created":"2020-05-18","cited_by_count":207},{"id":"2105.12655","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","created":"2021-05-25","cited_by_count":200},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159},{"id":"2310.06786","title":"OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text","created":"2023-10-10","cited_by_count":155},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136},{"id":"1812.06469","title":"The Adverse Effects of Code Duplication in Machine Learning Models of Code","created":"2018-12-16","cited_by_count":126},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114},{"id":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103},{"id":"2110.06773","title":"Leveraging Automated Unit Tests for Unsupervised Code Translation","created":"2021-10-13","cited_by_count":82},{"id":"2007.04973","title":"Contrastive Code Representation Learning","created":"2020-07-09","cited_by_count":76},{"id":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73},{"id":"1805.08490","title":"Generative Code Modeling with Graphs","created":"2018-05-22","cited_by_count":60},{"id":"1911.09983","title":"TreeGen: A Tree-Based Transformer Architecture for Code Generation","created":"2019-11-22","cited_by_count":58},{"id":"2206.07585","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","created":"2022-06-15","cited_by_count":54},{"id":"2312.12450","title":"Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions","created":"2023-12-11","cited_by_count":48},{"id":"2401.10440","title":"Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models","created":"2024-01-19","cited_by_count":38},{"id":"2206.05239","title":"StructCoder: Structure-Aware Transformer for Code Generation","created":"2022-06-10","cited_by_count":34},{"id":"1905.12386","title":"Misleading Authorship Attribution of Source Code using Adversarial Learning","created":"2019-05-29","cited_by_count":33},{"id":"2312.04730","title":"DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructions","created":"2023-12-07","cited_by_count":33},{"id":"2401.03003","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","created":"2024-01-05","cited_by_count":33},{"id":"2302.01973","title":"Measuring The Impact Of Programming Language Distribution","created":"2023-02-03","cited_by_count":32},{"id":"2204.09653","title":"On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages","created":"2022-04-05","cited_by_count":30},{"id":"2212.06742","title":"ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages","created":"2022-12-13","cited_by_count":29},{"id":"2306.03438","title":"Large Language Models of Code Fail at Completing Code with Potential Bugs","created":"2023-06-06","cited_by_count":29},{"id":"2205.10956","title":"CIRCLE: Continual Repair across Programming Languages","created":"2022-05-22","cited_by_count":17},{"id":"2007.13239","title":"funcGNN: A Graph Neural Network Approach to Program Similarity","created":"2020-07-26","cited_by_count":16},{"id":"2308.07655","title":"From Commit Message Generation to History-Aware Commit Message Completion","created":"2023-08-15","cited_by_count":16},{"id":"2012.04188","title":"Learning to Represent Programs with Heterogeneous Graphs","created":"2020-12-08","cited_by_count":14},{"id":"2402.05980","title":"Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates","created":"2024-02-08","cited_by_count":14},{"id":"2402.04141","title":"Multi-line AI-assisted Code Authoring","created":"2024-02-06","cited_by_count":13},{"id":"2204.09191","title":"Unleashing the Power of Compiler Intermediate Representation to Enhance Neural Program Embeddings","created":"2022-04-20","cited_by_count":10},{"id":"2309.15432","title":"ComPile: A Large IR Dataset from Production Sources","created":"2023-09-27","cited_by_count":10},{"id":"2306.06919","title":"Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization","created":"2023-06-12","cited_by_count":7},{"id":"2206.06460","title":"MetaTPTrans: A Meta Learning Approach for Multilingual Code Representation Learning","created":"2022-06-13","cited_by_count":6},{"id":"2110.08512","title":"AugmentedCode: Examining the Effects of Natural Language Resources in Code Retrieval Models","created":"2021-10-16","cited_by_count":3}],"next_cursor":null}