{"total":32,"rows":[{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159,"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":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91,"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":"2308.12261","title":"Prompt2Model: Generating Deployable Models from Natural Language Instructions","created":"2023-08-23","cited_by_count":41,"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":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36,"area":null},{"id":"2406.19073","title":"AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2302.01973","title":"Measuring The Impact Of Programming Language Distribution","created":"2023-02-03","cited_by_count":32,"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":"2308.16458","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","created":"2023-08-31","cited_by_count":25,"area":null},{"id":"2404.08018","title":"Analyzing the Performance of Large Language Models on Code Summarization","created":"2024-04-10","cited_by_count":19,"area":null},{"id":"2503.00691","title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","created":"2025-03-02","cited_by_count":11,"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":"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":"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":"2408.14504","title":"Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes","created":"2024-08-24","cited_by_count":5,"area":null},{"id":"2503.19217","title":"LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languages","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2505.04670","title":"LLM Code Customization with Visual Results: A Benchmark on TikZ","created":"2025-05-07","cited_by_count":5,"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":"2508.03678","title":"More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2407.05463","title":"Training Task Experts through Retrieval Based Distillation","created":"2024-07-07","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},{"id":"2307.04096","title":"Optimal Transport Posterior Alignment for Cross-lingual Semantic Parsing","created":"2023-07-09","cited_by_count":2,"area":null},{"id":"2503.04241","title":"ThrowBench: Benchmarking LLMs by Predicting Runtime Exceptions","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2505.11026","title":"StRuCom: A Novel Dataset of Structured Code Comments in Russian","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.19757","title":"CIDRe: A Reference-Free Multi-Aspect Criterion for Code Comment Quality Measurement","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2509.22768","title":"ML2B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.16787","title":"NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bangla Instruction to Python Code Generation","created":"2025-11-20","cited_by_count":0,"area":null}],"next_cursor":null}