{"list":"other","total":59,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"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":"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":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"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":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"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":"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":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"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":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159},{"id":"1601.01280","title":"Language to Logical Form with Neural Attention","created":"2016-01-06","cited_by_count":158},{"id":"2206.15331","title":"GitHub Copilot AI pair programmer: Asset or Liability?","created":"2022-06-30","cited_by_count":152},{"id":"2212.06800","title":"Diverse Demonstrations Improve In-context Compositional Generalization","created":"2022-12-13","cited_by_count":139},{"id":"2305.06599","title":"Structured Chain-of-Thought Prompting for Code Generation","created":"2023-05-11","cited_by_count":138},{"id":"2303.06689","title":"Self-planning Code Generation with Large Language Models","created":"2023-03-12","cited_by_count":124},{"id":"1805.04793","title":"Coarse-to-Fine Decoding for Neural Semantic Parsing","created":"2018-05-12","cited_by_count":110},{"id":"1808.09588","title":"Mapping Language to Code in Programmatic Context","created":"2018-08-29","cited_by_count":104},{"id":"2010.12412","title":"SmBoP: Semi-autoregressive Bottom-up Semantic Parsing","created":"2020-10-23","cited_by_count":97},{"id":"1810.02720","title":"TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation","created":"2018-10-05","cited_by_count":88},{"id":"2206.06888","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","created":"2022-06-14","cited_by_count":87},{"id":"2302.05020","title":"Impact of Code Language Models on Automated Program Repair","created":"2023-02-10","cited_by_count":85},{"id":"1603.06744","title":"Latent Predictor Networks for Code Generation","created":"2016-03-22","cited_by_count":73},{"id":"2305.14128","title":"Dr.ICL: Demonstration-Retrieved In-context Learning","created":"2023-05-23","cited_by_count":72},{"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":"2302.06144","title":"SkCoder: A Sketch-based Approach for Automatic Code Generation","created":"2023-02-13","cited_by_count":40},{"id":"2206.01335","title":"Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Code","created":"2022-06-02","cited_by_count":39},{"id":"2206.03865","title":"Fault-Aware Neural Code Rankers","created":"2022-06-04","cited_by_count":33},{"id":"2303.17780","title":"AceCoder: Utilizing Existing Code to Enhance Code Generation","created":"2023-03-31","cited_by_count":25},{"id":"2109.01657","title":"A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting","created":"2021-09-02","cited_by_count":21},{"id":"1401.0514","title":"Structured Generative Models of Natural Source Code","created":"2014-01-02","cited_by_count":19},{"id":"2106.00261","title":"Exploring Dynamic Selection of Branch Expansion Orders for Code Generation","created":"2021-06-01","cited_by_count":10},{"id":"2302.03908","title":"Syntax and Domain Aware Model for Unsupervised Program Translation","created":"2023-02-08","cited_by_count":7},{"id":"1510.07211","title":"On End-to-End Program Generation from User Intention by Deep Neural Networks","created":"2015-10-25","cited_by_count":6},{"id":"2202.07612","title":"CodeGen-Test: An Automatic Code Generation Model Integrating Program Test Information","created":"2022-02-14","cited_by_count":3},{"id":"2308.13754","title":"ZC3: Zero-Shot Cross-Language Code Clone Detection","created":"2023-08-26","cited_by_count":3}],"next_cursor":null}