{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"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":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"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":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"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":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","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":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"1709.06182","title":"A Survey of Machine Learning for Big Code and Naturalness","created":"2017-09-18","cited_by_count":221},{"id":"2206.15000","title":"Grounded Copilot: How Programmers Interact with Code-Generating Models","created":"2022-06-30","cited_by_count":218},{"id":"1805.08949","title":"Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow","created":"2018-05-23","cited_by_count":165},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159},{"id":"2204.00498","title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","created":"2022-03-15","cited_by_count":101},{"id":"1811.07234","title":"Improving Automatic Source Code Summarization via Deep Reinforcement Learning","created":"2018-11-17","cited_by_count":100},{"id":"2203.09095","title":"Automating Code Review Activities by Large-Scale Pre-training","created":"2022-03-17","cited_by_count":98},{"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":"2206.06888","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","created":"2022-06-14","cited_by_count":87},{"id":"2211.02265","title":"Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book","created":"2022-11-04","cited_by_count":84},{"id":"2010.03150","title":"PyMT5: multi-mode translation of natural language and Python code with transformers","created":"2020-10-07","cited_by_count":80},{"id":"2204.00056","title":"SELFIES and the future of molecular string representations","created":"2022-03-31","cited_by_count":76},{"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":"2206.08474","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","created":"2022-06-16","cited_by_count":56},{"id":"2002.05442","title":"Deep Learning for Source Code Modeling and Generation: Models, Applications and Challenges","created":"2020-02-13","cited_by_count":55},{"id":"2210.17236","title":"When Language Model Meets Private Library","created":"2022-10-31","cited_by_count":54},{"id":"1910.02216","title":"JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation","created":"2019-10-05","cited_by_count":49},{"id":"2207.11280","title":"PanGu-Coder: Program Synthesis with Function-Level Language Modeling","created":"2022-07-22","cited_by_count":48},{"id":"2203.08388","title":"MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages","created":"2022-03-16","cited_by_count":41},{"id":"2201.12901","title":"Training and Evaluating a Jupyter Notebook Data Science Assistant","created":"2022-01-30","cited_by_count":31},{"id":"1811.06837","title":"A Grammar-Based Structural CNN Decoder for Code Generation","created":"2018-11-14","cited_by_count":29},{"id":"2212.06742","title":"ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages","created":"2022-12-13","cited_by_count":29},{"id":"1603.06075","title":"Tree-to-Sequence Attentional Neural Machine Translation","created":"2016-03-19","cited_by_count":28},{"id":"2209.14876","title":"Repairing Bugs in Python Assignments Using Large Language Models","created":"2022-09-29","cited_by_count":28},{"id":"2111.03922","title":"Automatic Program Repair with OpenAI's Codex: Evaluating QuixBugs","created":"2021-11-06","cited_by_count":25},{"id":"2110.09610","title":"A Survey on Machine Learning Techniques for Source Code Analysis","created":"2021-10-18","cited_by_count":24},{"id":"2111.07875","title":"Choose Your Programming Copilot: A Comparison of the Program Synthesis Performance of GitHub Copilot and Genetic Programming","created":"2021-11-15","cited_by_count":24},{"id":"1404.0417","title":"Mining Idioms from Source Code","created":"2014-04-01","cited_by_count":19},{"id":"2111.08171","title":"Solving Linear Algebra by Program Synthesis","created":"2021-11-16","cited_by_count":14},{"id":"1703.06353","title":"Systematic Mapping Study of Template-based Code Generation","created":"2017-03-18","cited_by_count":4},{"id":"2207.04285","title":"A Closer Look into Transformer-Based Code Intelligence Through Code Transformation: Challenges and Opportunities","created":"2022-07-09","cited_by_count":1}],"next_cursor":null}