{"total":141,"rows":[{"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":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498,"area":null},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2402.16347","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","created":"2024-02-26","cited_by_count":187,"area":null},{"id":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178,"area":null},{"id":"2308.01861","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation","created":"2023-08-03","cited_by_count":168,"area":null},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159,"area":null},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153,"area":null},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138,"area":null},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136,"area":null},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128,"area":null},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124,"area":null},{"id":"2302.05527","title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","created":"2023-02-10","cited_by_count":102,"area":null},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91,"area":null},{"id":"2105.13239","title":"CoSQA: 20,000+ Web Queries for Code Search and Question Answering","created":"2021-05-27","cited_by_count":75,"area":null},{"id":"2308.10335","title":"Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation","created":"2023-08-20","cited_by_count":73,"area":null},{"id":"2404.00599","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-03-31","cited_by_count":72,"area":null},{"id":"2405.19856","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-05-30","cited_by_count":72,"area":null},{"id":"2208.03133","title":"Out of the BLEU: how should we assess quality of the Code Generation models?","created":"2022-08-05","cited_by_count":65,"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":"2304.14317","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","created":"2023-04-27","cited_by_count":52,"area":null},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"area":null},{"id":"2410.02184","title":"CodeJudge: Evaluating Code Generation with Large Language Models","created":"2024-10-03","cited_by_count":44,"area":null},{"id":"2306.02907","title":"SelfEvolve: A Code Evolution Framework via Large Language Models","created":"2023-06-05","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":"2203.08388","title":"MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages","created":"2022-03-16","cited_by_count":41,"area":null},{"id":"2403.01081","title":"LAB: Large-Scale Alignment for ChatBots","created":"2024-03-02","cited_by_count":39,"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":"2410.22821","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","created":"2024-10-30","cited_by_count":34,"area":null},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2211.09374","title":"Execution-based Evaluation for Data Science Code Generation Models","created":"2022-11-17","cited_by_count":32,"area":null},{"id":"2302.01973","title":"Measuring The Impact Of Programming Language Distribution","created":"2023-02-03","cited_by_count":32,"area":null},{"id":"2202.06649","title":"On the Importance of Building High-quality Training Datasets for Neural Code Search","created":"2022-02-14","cited_by_count":30,"area":null},{"id":"2212.06742","title":"ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages","created":"2022-12-13","cited_by_count":29,"area":null},{"id":"2308.10462","title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models","created":"2023-08-21","cited_by_count":28,"area":null},{"id":"2403.16443","title":"CodeS: Natural Language to Code Repository via Multi-Layer Sketch","created":"2024-03-25","cited_by_count":28,"area":null},{"id":"2404.08817","title":"Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance","created":"2024-04-12","cited_by_count":26,"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":"2404.09696","title":"Are Large Language Models Reliable Argument Quality Annotators?","created":"2024-04-15","cited_by_count":24,"area":null},{"id":"2406.16386","title":"Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach","created":"2024-06-24","cited_by_count":24,"area":null},{"id":"2105.14220","title":"CoDesc: A Large Code-Description Parallel Dataset","created":"2021-05-29","cited_by_count":23,"area":null},{"id":"2404.00566","title":"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks","created":"2024-03-31","cited_by_count":23,"area":null},{"id":"2309.17446","title":"L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models","created":"2023-09-29","cited_by_count":22,"area":null},{"id":"2406.11927","title":"On the Impacts of Contexts on Repository-Level Code Generation","created":"2024-06-17","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":"2503.17181","title":"A Study of LLMs' Preferences for Libraries and Programming Languages","created":"2025-03-21","cited_by_count":20,"area":null},{"id":"2405.04520","title":"NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts","created":"2024-05-07","cited_by_count":19,"area":null},{"id":"2212.09885","title":"Python Code Generation by Asking Clarification Questions","created":"2022-12-19","cited_by_count":17,"area":null},{"id":"2401.04514","title":"Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search","created":"2024-01-09","cited_by_count":17,"area":null},{"id":"2406.07411","title":"VersiCode: Towards Version-controllable Code Generation","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2104.13100","title":"Shellcode_IA32: A Dataset for Automatic Shellcode Generation","created":"2021-04-27","cited_by_count":16,"area":null},{"id":"2402.13013","title":"Code Needs Comments: Enhancing Code LLMs with Comment Augmentation","created":"2024-02-20","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":"2310.14495","title":"InstructExcel: A Benchmark for Natural Language Instruction in Excel","created":"2023-10-23","cited_by_count":15,"area":null},{"id":"2305.11790","title":"Prompting with Pseudo-Code Instructions","created":"2023-05-19","cited_by_count":14,"area":null},{"id":"2403.16702","title":"ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search","created":"2024-03-25","cited_by_count":12,"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":"2503.13733","title":"CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2508.03121","title":"RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging","created":"2025-08-05","cited_by_count":11,"area":null},{"id":"2106.00261","title":"Exploring Dynamic Selection of Branch Expansion Orders for Code Generation","created":"2021-06-01","cited_by_count":10,"area":null},{"id":"2402.19431","title":"Compositional API Recommendation for Library-Oriented Code Generation","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2406.12902","title":"JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2411.06638","title":"Model Editing for LLMs4Code: How Far are We?","created":"2024-11-11","cited_by_count":10,"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":"2401.06401","title":"DevEval: Evaluating Code Generation in Practical Software Projects","created":"2024-01-12","cited_by_count":9,"area":null},{"id":"2403.00894","title":"Comparing large language models and human programmers for generating programming code","created":"2024-03-01","cited_by_count":9,"area":null},{"id":"2106.04447","title":"Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation","created":"2021-06-08","cited_by_count":8,"area":null},{"id":"2401.06786","title":"CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation","created":"2023-11-10","cited_by_count":8,"area":null},{"id":"2508.21085","title":"Granite Embedding R2 Models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2601.11895","title":"DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2211.00818","title":"CodePAD: Sequence-based Code Generation with Pushdown Automaton","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2101.00259","title":"Code Generation from Natural Language with Less Prior and More Monolingual Data","created":"2021-01-01","cited_by_count":6,"area":null},{"id":"2310.16673","title":"Exploring Large Language Models for Code Explanation","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2411.05830","title":"GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2108.12144","title":"Lyra: A Benchmark for Turducken-Style Code Generation","created":"2021-08-27","cited_by_count":5,"area":null},{"id":"2110.04353","title":"Learning to Describe Solutions for Bug Reports Based on Developer Discussions","created":"2021-10-08","cited_by_count":5,"area":null},{"id":"2306.04085","title":"XSemPLR: Cross-Lingual Semantic Parsing in Multiple Natural Languages and Meaning Representations","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2312.05356","title":"Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2506.14280","title":"Improving LoRA with Variational Learning","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2507.20888","title":"Enhancing Project-Specific Code Completion by Inferring Internal API Information","created":"2025-07-28","cited_by_count":5,"area":null},{"id":"2511.21285","title":"PEFT-Bench: A Parameter-Efficient Fine-Tuning Methods Benchmark","created":"2025-11-26","cited_by_count":5,"area":null},{"id":"2108.05198","title":"Natural Language-Guided Programming","created":"2021-08-11","cited_by_count":4,"area":null},{"id":"2205.01293","title":"A Survey of Deep Learning Models for Structural Code Understanding","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2303.12869","title":"JaCoText: A Pretrained Model for Java Code-Text Generation","created":"2023-03-22","cited_by_count":4,"area":null},{"id":"2404.18766","title":"PECC: Problem Extraction and Coding Challenges","created":"2024-04-29","cited_by_count":4,"area":null},{"id":"2409.16819","title":"CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2101.09571","title":"BF++: a language for general-purpose program synthesis","created":"2021-01-23","cited_by_count":3,"area":null},{"id":"2202.04847","title":"A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2202.07806","title":"Code Generation for Unknown Libraries via Reading API Documentations","created":"2022-02-16","cited_by_count":3,"area":null},{"id":"2205.10674","title":"NS3: Neuro-Symbolic Semantic Code Search","created":"2022-05-21","cited_by_count":3,"area":null},{"id":"2206.13354","title":"Transformer with Tree-order Encoding for Neural Program Generation","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2208.05596","title":"Finding Reusable Machine Learning Components to Build Programming Language Processing Pipelines","created":"2022-08-11","cited_by_count":3,"area":null},{"id":"2302.07845","title":"NL2CMD: An Updated Workflow for Natural Language to Bash Commands Translation","created":"2023-02-15","cited_by_count":3,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2401.10716","title":"Structured Code Representations Enable Data-Efficient Adaptation of Code Language Models","created":"2024-01-19","cited_by_count":3,"area":null},{"id":"2409.13551","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","created":"2024-09-20","cited_by_count":3,"area":null}],"next_cursor":"100"}