{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"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":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"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":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"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":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"1704.00051","title":"Reading Wikipedia to Answer Open-Domain Questions","created":"2017-03-31","cited_by_count":777},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"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":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"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":"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":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"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":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153},{"id":"2309.12499","title":"CodePlan: Repository-level Coding using LLMs and Planning","created":"2023-09-21","cited_by_count":140},{"id":"2211.14876","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","created":"2022-11-27","cited_by_count":136},{"id":"2205.12035","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","created":"2022-05-24","cited_by_count":118},{"id":"1808.09588","title":"Mapping Language to Code in Programmatic Context","created":"2018-08-29","cited_by_count":104},{"id":"1704.07535","title":"Abstract Syntax Networks for Code Generation and Semantic Parsing","created":"2017-04-25","cited_by_count":92},{"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":"1603.06744","title":"Latent Predictor Networks for Code Generation","created":"2016-03-22","cited_by_count":73},{"id":"1812.01194","title":"A Retrieve-and-Edit Framework for Predicting Structured Outputs","created":"2018-12-04","cited_by_count":73},{"id":"1911.09983","title":"TreeGen: A Tree-Based Transformer Architecture for Code Generation","created":"2019-11-22","cited_by_count":58},{"id":"2206.08474","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","created":"2022-06-16","cited_by_count":56},{"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":"2304.07575","title":"What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?","created":"2023-04-15","cited_by_count":47},{"id":"1808.10025","title":"Retrieval-Based Neural Code Generation","created":"2018-08-29","cited_by_count":41},{"id":"2203.08388","title":"MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages","created":"2022-03-16","cited_by_count":41},{"id":"2302.06144","title":"SkCoder: A Sketch-based Approach for Automatic Code Generation","created":"2023-02-13","cited_by_count":40},{"id":"2302.04026","title":"An Empirical Comparison of Pre-Trained Models of Source Code","created":"2023-02-08","cited_by_count":25},{"id":"2011.02297","title":"Opportunities and Challenges in Code Search Tools","created":"2020-11-04","cited_by_count":22},{"id":"2204.03293","title":"CoCoSoDa: Effective Contrastive Learning for Code Search","created":"2022-04-07","cited_by_count":22},{"id":"1904.09086","title":"Learning Programmatic Idioms for Scalable Semantic Parsing","created":"2019-04-19","cited_by_count":17},{"id":"1808.09492","title":"Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering","created":"2018-08-28","cited_by_count":12},{"id":"2104.05310","title":"Generating Code with the Help of Retrieved Template Functions and Stack Overflow Answers","created":"2021-04-12","cited_by_count":3}],"next_cursor":null}