{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"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":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"1511.06709","title":"Improving Neural Machine Translation Models with Monolingual Data","created":"2015-11-20","cited_by_count":788},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2108.09293","title":"Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions","created":"2021-08-20","cited_by_count":431},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2202.13169","title":"A Systematic Evaluation of Large Language Models of Code","created":"2022-02-26","cited_by_count":363},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2006.03511","title":"Unsupervised Translation of Programming Languages","created":"2020-06-05","cited_by_count":263},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"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":"2205.12628","title":"Are Large Pre-Trained Language Models Leaking Your Personal Information?","created":"2022-05-25","cited_by_count":200},{"id":"1906.04908","title":"SPoC: Search-based Pseudocode to Code","created":"2019-06-12","cited_by_count":176},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153},{"id":"1611.01989","title":"DeepCoder: Learning to Write Programs","created":"2016-11-07","cited_by_count":149},{"id":"2108.11601","title":"Retrieval Augmented Code Generation and Summarization","created":"2021-08-26","cited_by_count":149},{"id":"2206.11861","title":"Automatic Generation of Programming Exercises and Code Explanations using Large Language Models","created":"2022-06-03","cited_by_count":126},{"id":"2111.09509","title":"How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN","created":"2021-11-18","cited_by_count":124},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124},{"id":"2112.02125","title":"Examining Zero-Shot Vulnerability Repair with Large Language Models","created":"2021-12-03","cited_by_count":105},{"id":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103},{"id":"2112.15594","title":"A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level","created":"2021-12-31","cited_by_count":96},{"id":"2110.06773","title":"Leveraging Automated Unit Tests for Unsupervised Code Translation","created":"2021-10-13","cited_by_count":82},{"id":"2102.01818","title":"Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation","created":"2021-02-03","cited_by_count":70},{"id":"2102.02017","title":"Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks","created":"2021-02-03","cited_by_count":70},{"id":"2208.11640","title":"Repair Is Nearly Generation: Multilingual Program Repair with LLMs","created":"2022-08-24","cited_by_count":68},{"id":"2302.00438","title":"On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot","created":"2023-02-01","cited_by_count":64},{"id":"2108.04556","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","created":"2021-08-10","cited_by_count":63},{"id":"1910.05923","title":"Code Generation as a Dual Task of Code Summarization","created":"2019-10-14","cited_by_count":62},{"id":"2105.08645","title":"CoTexT: Multi-task Learning with Code-Text Transformer","created":"2021-05-18","cited_by_count":61},{"id":"2207.11280","title":"PanGu-Coder: Program Synthesis with Function-Level Language Modeling","created":"2022-07-22","cited_by_count":48},{"id":"2203.05132","title":"Compilable Neural Code Generation with Compiler Feedback","created":"2022-03-10","cited_by_count":47},{"id":"2105.12485","title":"TreeBERT: A Tree-Based Pre-Trained Model for Programming Language","created":"2021-05-26","cited_by_count":41},{"id":"2108.11308","title":"What do pre-trained code models know about code?","created":"2021-08-25","cited_by_count":36},{"id":"2202.08975","title":"Probing Pretrained Models of Source Code","created":"2022-02-16","cited_by_count":26},{"id":"2203.08597","title":"Less is More: Summary of Long Instructions is Better for Program Synthesis","created":"2022-03-16","cited_by_count":17},{"id":"2111.08171","title":"Solving Linear Algebra by Program Synthesis","created":"2021-11-16","cited_by_count":14},{"id":"2212.02684","title":"Codex Hacks HackerRank: Memorization Issues and a Framework for Code Synthesis Evaluation","created":"2022-12-06","cited_by_count":14},{"id":"2204.06894","title":"To What Extent do Deep Learning-based Code Recommenders Generate Predictions by Cloning Code from the Training Set?","created":"2022-04-14","cited_by_count":11},{"id":"2211.00609","title":"A Simple, Yet Effective Approach to Finding Biases in Code Generation","created":"2022-10-31","cited_by_count":8},{"id":"1710.05913","title":"A Survey on Online Judge Systems and Their Applications","created":"2017-10-14","cited_by_count":7},{"id":"2202.07806","title":"Code Generation for Unknown Libraries via Reading API Documentations","created":"2022-02-16","cited_by_count":3}],"next_cursor":null}