{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"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":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"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":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"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":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"1905.03197","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","created":"2019-05-08","cited_by_count":670},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255},{"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":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124},{"id":"1808.09588","title":"Mapping Language to Code in Programmatic Context","created":"2018-08-29","cited_by_count":104},{"id":"2112.02969","title":"Jigsaw: Large Language Models meet Program Synthesis","created":"2021-12-06","cited_by_count":103},{"id":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103},{"id":"1802.08979","title":"NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System","created":"2018-02-25","cited_by_count":98},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91},{"id":"2212.09248","title":"Natural Language to Code Generation in Interactive Data Science Notebooks","created":"2022-12-19","cited_by_count":87},{"id":"1611.01855","title":"Neuro-Symbolic Program Synthesis","created":"2016-11-06","cited_by_count":84},{"id":"2105.13239","title":"CoSQA: 20,000+ Web Queries for Code Search and Question Answering","created":"2021-05-27","cited_by_count":75},{"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":"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":"2304.07575","title":"What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?","created":"2023-04-15","cited_by_count":47},{"id":"2203.08388","title":"MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages","created":"2022-03-16","cited_by_count":41},{"id":"2207.11680","title":"No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligence","created":"2022-07-24","cited_by_count":41},{"id":"2107.00101","title":"Latent Execution for Neural Program Synthesis","created":"2021-06-29","cited_by_count":35},{"id":"2309.10094","title":"Data Formulator: AI-powered Concept-driven Visualization Authoring","created":"2023-09-18","cited_by_count":32},{"id":"2003.09040","title":"TF-Coder: Program Synthesis for Tensor Manipulations","created":"2020-03-19","cited_by_count":27},{"id":"2102.12592","title":"Documentation Matters: Human-Centered AI System to Assist Data Science Code Documentation in Computational Notebooks","created":"2021-02-24","cited_by_count":17},{"id":"2112.01590","title":"The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Large","created":"2021-12-02","cited_by_count":17},{"id":"2210.05197","title":"Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA","created":"2022-10-11","cited_by_count":17},{"id":"2309.07639","title":"Your Code Secret Belongs to Me: Neural Code Completion Tools Can Memorize Hard-Coded Credentials","created":"2023-09-14","cited_by_count":17},{"id":"2110.08381","title":"On The Ingredients of an Effective Zero-shot Semantic Parser","created":"2021-10-15","cited_by_count":13},{"id":"2305.01598","title":"From Words to Code: Harnessing Data for Program Synthesis from Natural Language","created":"2023-05-02","cited_by_count":11},{"id":"2402.03630","title":"Enhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context","created":"2024-02-06","cited_by_count":10},{"id":"2307.05950","title":"Exploring the Effectiveness of LLMs in Automated Logging Generation: An Empirical Study","created":"2023-07-12","cited_by_count":9},{"id":"2402.12958","title":"Go Static: Contextualized Logging Statement Generation","created":"2024-02-20","cited_by_count":9},{"id":"2112.07858","title":"EDAssistant: Supporting Exploratory Data Analysis in Computational Notebooks with In-Situ Code Search and Recommendation","created":"2021-12-15","cited_by_count":8},{"id":"2110.08339","title":"A Static Analysis Framework for Data Science Notebooks","created":"2021-10-15","cited_by_count":4},{"id":"2201.03758","title":"Predictive Synthesis of API-Centric Code","created":"2022-01-11","cited_by_count":4},{"id":"2112.14825","title":"ReSplit: Improving the Structure of Jupyter Notebooks by Re-Splitting Their Cells","created":"2021-12-29","cited_by_count":3},{"id":"2305.03039","title":"SuperNOVA: Design Strategies and Opportunities for Interactive Visualization in Computational Notebooks","created":"2023-05-04","cited_by_count":3},{"id":"2310.18079","title":"Supporting Better Insights of Data Science Pipelines with Fine-grained Provenance","created":"2023-10-27","cited_by_count":3}],"next_cursor":null}