{"total":189,"rows":[{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637,"area":null},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417,"area":null},{"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,"area":null},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367,"area":null},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361,"area":null},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358,"area":null},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353,"area":null},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333,"area":null},{"id":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300,"area":null},{"id":"2302.06527","title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","created":"2023-02-13","cited_by_count":194,"area":null},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138,"area":null},{"id":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112,"area":null},{"id":"2301.13816","title":"Execution-based Code Generation using Deep Reinforcement Learning","created":"2023-01-31","cited_by_count":99,"area":null},{"id":"2203.09095","title":"Automating Code Review Activities by Large-Scale Pre-training","created":"2022-03-17","cited_by_count":98,"area":null},{"id":"2205.06537","title":"Productivity Assessment of Neural Code Completion","created":"2022-05-13","cited_by_count":98,"area":null},{"id":"2304.11938","title":"Is ChatGPT the Ultimate Programming Assistant -- How far is it?","created":"2023-04-24","cited_by_count":76,"area":null},{"id":"2108.04556","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","created":"2021-08-10","cited_by_count":63,"area":null},{"id":"2410.05340","title":"Generating CAD Code with Vision-Language Models for 3D Designs","created":"2024-10-07","cited_by_count":62,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2202.06689","title":"CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences","created":"2022-02-14","cited_by_count":50,"area":null},{"id":"2203.05132","title":"Compilable Neural Code Generation with Compiler Feedback","created":"2022-03-10","cited_by_count":47,"area":null},{"id":"2310.09748","title":"Large Language Model-Aware In-Context Learning for Code Generation","created":"2023-10-15","cited_by_count":43,"area":null},{"id":"2106.15339","title":"SpreadsheetCoder: Formula Prediction from Semi-structured Context","created":"2021-06-26","cited_by_count":41,"area":null},{"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,"area":null},{"id":"2306.10998","title":"RepoFusion: Training Code Models to Understand Your Repository","created":"2023-06-19","cited_by_count":40,"area":null},{"id":"2402.16197","title":"Language Models for Code Completion: A Practical Evaluation","created":"2024-02-25","cited_by_count":39,"area":null},{"id":"2201.12438","title":"Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey","created":"2022-01-28","cited_by_count":38,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2108.11308","title":"What do pre-trained code models know about code?","created":"2021-08-25","cited_by_count":36,"area":null},{"id":"2305.05383","title":"Code Execution with Pre-trained Language Models","created":"2023-05-08","cited_by_count":34,"area":null},{"id":"2502.18658","title":"Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support","created":"2025-02-25","cited_by_count":34,"area":null},{"id":"2312.04730","title":"DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructions","created":"2023-12-07","cited_by_count":33,"area":null},{"id":"2307.02503","title":"Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review","created":"2023-07-04","cited_by_count":32,"area":null},{"id":"2201.12901","title":"Training and Evaluating a Jupyter Notebook Data Science Assistant","created":"2022-01-30","cited_by_count":31,"area":null},{"id":"2302.10166","title":"Learning Deep Semantics for Test Completion","created":"2023-02-20","cited_by_count":31,"area":null},{"id":"2103.09499","title":"Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs","created":"2021-03-17","cited_by_count":30,"area":null},{"id":"2204.09653","title":"On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages","created":"2022-04-05","cited_by_count":30,"area":null},{"id":"2306.03438","title":"Large Language Models of Code Fail at Completing Code with Potential Bugs","created":"2023-06-06","cited_by_count":29,"area":null},{"id":"2311.11690","title":"Refactoring Programs Using Large Language Models with Few-Shot Examples","created":"2023-11-20","cited_by_count":28,"area":null},{"id":"2305.00909","title":"Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation","created":"2023-04-28","cited_by_count":27,"area":null},{"id":"2105.04297","title":"How could Neural Networks understand Programs?","created":"2021-05-10","cited_by_count":26,"area":null},{"id":"2308.12247","title":"How to Protect Copyright Data in Optimization of Large Language Models?","created":"2023-08-23","cited_by_count":26,"area":null},{"id":"2106.05784","title":"Programming Puzzles","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2108.06645","title":"On Multi-Modal Learning of Editing Source Code","created":"2021-08-15","cited_by_count":25,"area":null},{"id":"2205.10162","title":"FedAdapter: Efficient Federated Learning for Modern NLP","created":"2022-05-20","cited_by_count":25,"area":null},{"id":"2110.09610","title":"A Survey on Machine Learning Techniques for Source Code Analysis","created":"2021-10-18","cited_by_count":24,"area":null},{"id":"2106.10158","title":"Learning to Complete Code with Sketches","created":"2021-06-18","cited_by_count":23,"area":null},{"id":"2306.06755","title":"CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution","created":"2023-06-11","cited_by_count":22,"area":null},{"id":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2201.10866","title":"CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search","created":"2022-01-26","cited_by_count":21,"area":null},{"id":"2205.11739","title":"Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code","created":"2022-05-24","cited_by_count":21,"area":null},{"id":"2304.05216","title":"Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond","created":"2023-04-11","cited_by_count":20,"area":null},{"id":"2406.19783","title":"NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations","created":"2024-06-28","cited_by_count":20,"area":null},{"id":"2104.07896","title":"Generating Bug-Fixes Using Pretrained Transformers","created":"2021-04-16","cited_by_count":18,"area":null},{"id":"2410.01353","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2105.09352","title":"DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons","created":"2021-05-19","cited_by_count":17,"area":null},{"id":"2303.15822","title":"One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2308.07655","title":"From Commit Message Generation to History-Aware Commit Message Completion","created":"2023-08-15","cited_by_count":16,"area":null},{"id":"2408.09121","title":"Selective Prompt Anchoring for Code Generation","created":"2024-08-17","cited_by_count":16,"area":null},{"id":"2503.17502","title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","created":"2025-03-21","cited_by_count":16,"area":null},{"id":"2205.02029","title":"CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training","created":"2022-05-04","cited_by_count":15,"area":null},{"id":"2212.05974","title":"Federated Few-Shot Learning for Mobile NLP","created":"2022-12-12","cited_by_count":15,"area":null},{"id":"2301.13779","title":"FLAME: A small language model for spreadsheet formulas","created":"2023-01-31","cited_by_count":15,"area":null},{"id":"2109.08780","title":"Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy","created":"2021-09-17","cited_by_count":14,"area":null},{"id":"2210.16494","title":"Aligning Offline Metrics and Human Judgments of Value for Code Generation Models","created":"2022-10-29","cited_by_count":14,"area":null},{"id":"2306.00381","title":"Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completion","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2401.12947","title":"Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion","created":"2024-01-23","cited_by_count":14,"area":null},{"id":"2402.18062","title":"Generative AI for Unmanned Vehicle Swarms: Challenges, Applications and Opportunities","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2111.01633","title":"Neural Program Generation Modulo Static Analysis","created":"2021-10-26","cited_by_count":13,"area":null},{"id":"2212.10079","title":"A Survey on Pretrained Language Models for Neural Code Intelligence","created":"2022-12-20","cited_by_count":13,"area":null},{"id":"2306.01754","title":"Transformer-based Vulnerability Detection in Code at EditTime: Zero-shot, Few-shot, or Fine-tuning?","created":"2023-05-23","cited_by_count":13,"area":null},{"id":"2203.09907","title":"Learning to Reduce False Positives in Analytic Bug Detectors","created":"2022-03-08","cited_by_count":12,"area":null},{"id":"2208.10091","title":"Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generation","created":"2022-08-22","cited_by_count":11,"area":null},{"id":"2212.06008","title":"Who Evaluates the Evaluators? On Automatic Metrics for Assessing AI-based Offensive Code Generators","created":"2022-12-12","cited_by_count":11,"area":null},{"id":"2409.06741","title":"Generative AI for Requirements Engineering: A Systematic Literature Review","created":"2024-09-10","cited_by_count":11,"area":null},{"id":"2106.04985","title":"Energy-Based Models for Code Generation under Compilability Constraints","created":"2021-06-09","cited_by_count":10,"area":null},{"id":"2211.04673","title":"Syntax-Aware On-the-Fly Code Completion","created":"2022-11-09","cited_by_count":10,"area":null},{"id":"2303.00732","title":"R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents","created":"2023-03-01","cited_by_count":10,"area":null},{"id":"2311.12890","title":"De-fine: Decomposing and Refining Visual Programs with Auto-Feedback","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2406.09606","title":"Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2409.15204","title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","created":"2024-09-23","cited_by_count":10,"area":null},{"id":"2112.08273","title":"Programming Knowledge Tracing: A Comprehensive Dataset and A New Model","created":"2021-12-11","cited_by_count":9,"area":null},{"id":"2204.03498","title":"On the Effectiveness of Pretrained Models for API Learning","created":"2022-04-05","cited_by_count":9,"area":null},{"id":"2205.10692","title":"All You Need Is Logs: Improving Code Completion by Learning from Anonymous IDE Usage Logs","created":"2022-05-21","cited_by_count":9,"area":null},{"id":"2212.10017","title":"Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities","created":"2022-12-20","cited_by_count":9,"area":null},{"id":"2307.08260","title":"Extending the Frontier of ChatGPT: Code Generation and Debugging","created":"2023-07-17","cited_by_count":9,"area":null},{"id":"2310.17903","title":"Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey","created":"2023-10-27","cited_by_count":9,"area":null},{"id":"2310.18752","title":"Reboost Large Language Model-based Text-to-SQL, Text-to-Python, and Text-to-Function -- with Real Applications in Traffic Domain","created":"2023-10-28","cited_by_count":9,"area":null},{"id":"2311.00684","title":"Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation","created":"2023-11-01","cited_by_count":9,"area":null},{"id":"2209.10254","title":"T5QL: Taming language models for SQL generation","created":"2022-09-21","cited_by_count":8,"area":null},{"id":"2302.04048","title":"Automating Code-Related Tasks Through Transformers: The Impact of Pre-training","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2304.12269","title":"Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2401.15545","title":"PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models","created":"2024-01-28","cited_by_count":8,"area":null},{"id":"2401.16960","title":"Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment","created":"2024-01-30","cited_by_count":8,"area":null},{"id":"2402.13352","title":"KetGPT - Dataset Augmentation of Quantum Circuits using Transformers","created":"2024-02-20","cited_by_count":8,"area":null},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null}],"next_cursor":"100"}