{"total":108,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"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":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2312.14033","title":"T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step","created":"2023-12-21","cited_by_count":93,"area":null},{"id":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93,"area":null},{"id":"2403.04797","title":"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding","created":"2024-03-05","cited_by_count":72,"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":"2502.06193","title":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","created":"2025-02-10","cited_by_count":67,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2403.08937","title":"Bugs in Large Language Models Generated Code: An Empirical Study","created":"2024-03-13","cited_by_count":60,"area":null},{"id":"2503.06680","title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","created":"2025-03-09","cited_by_count":58,"area":null},{"id":"2412.01769","title":"Commit0: Library Generation from Scratch","created":"2024-12-02","cited_by_count":52,"area":null},{"id":"2411.03292","title":"Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping","created":"2024-11-05","cited_by_count":51,"area":null},{"id":"2403.16792","title":"Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback","created":"2024-03-25","cited_by_count":46,"area":null},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2311.08588","title":"CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation","created":"2023-11-14","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":"2401.12554","title":"Can Large Language Models Write Parallel Code?","created":"2024-01-23","cited_by_count":36,"area":null},{"id":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36,"area":null},{"id":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31,"area":null},{"id":"2503.01245","title":"Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications","created":"2025-03-03","cited_by_count":26,"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":"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":"2404.00566","title":"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks","created":"2024-03-31","cited_by_count":23,"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":"2401.06437","title":"3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?","created":"2024-01-12","cited_by_count":21,"area":null},{"id":"2408.13204","title":"DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation","created":"2024-08-23","cited_by_count":21,"area":null},{"id":"2406.12655","title":"Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2407.06249","title":"CodeUpdateArena: Benchmarking Knowledge Editing on API Updates","created":"2024-07-08","cited_by_count":19,"area":null},{"id":"2504.15254","title":"CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation","created":"2025-04-21","cited_by_count":19,"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":"2503.06689","title":"DependEval: Benchmarking LLMs for Repository Dependency Understanding","created":"2025-03-09","cited_by_count":17,"area":null},{"id":"2308.10345","title":"Can Large Language Models Find And Fix Vulnerable Software?","created":"2023-08-20","cited_by_count":15,"area":null},{"id":"2407.00456","title":"Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models","created":"2024-06-29","cited_by_count":15,"area":null},{"id":"2503.22688","title":"CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation","created":"2025-03-05","cited_by_count":15,"area":null},{"id":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2503.07358","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2408.00019","title":"WebApp1K: A Practical Code-Generation Benchmark for Web App Development","created":"2024-07-30","cited_by_count":11,"area":null},{"id":"2504.20799","title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","created":"2025-04-29","cited_by_count":11,"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":"2407.11470","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","created":"2024-07-16","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":"2312.14856","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code","created":"2023-12-22","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":"2412.17315","title":"CodeV: Issue Resolving with Visual Data","created":"2024-12-23","cited_by_count":9,"area":null},{"id":"2403.13583","title":"CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2502.16704","title":"Code Summarization Beyond Function Level","created":"2025-02-23","cited_by_count":8,"area":null},{"id":"2506.02073","title":"Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2510.26130","title":"Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation","created":"2025-10-30","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":"2407.03611","title":"An Empirical Study on Capability of Large Language Models in Understanding Code Semantics","created":"2024-07-04","cited_by_count":7,"area":null},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2501.13699","title":"DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale","created":"2025-01-23","cited_by_count":7,"area":null},{"id":"2503.10452","title":"DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation","created":"2025-03-13","cited_by_count":7,"area":null},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","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":"2411.03012","title":"Leveraging Large Language Models in Code Question Answering: Baselines and Issues","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2509.22237","title":"FeatBench: Towards More Realistic Evaluation of Feature-level Code Generation","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2402.03130","title":"User Centric Evaluation of Code Generation Tools","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2407.04831","title":"Code Hallucination","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2410.15154","title":"MCCoder: Streamlining Motion Control with LLM-Assisted Code Generation and Rigorous Verification","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2505.04406","title":"YABLoCo: Yet Another Benchmark for Long Context Code Generation","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2505.09027","title":"Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation","created":"2025-05-13","cited_by_count":5,"area":null},{"id":"2404.03114","title":"Testing the Effect of Code Documentation on Large Language Model Code Understanding","created":"2024-04-03","cited_by_count":4,"area":null},{"id":"2408.15630","title":"CodeSift: An LLM-Based Reference-Less Framework for Automatic Code Validation","created":"2024-08-28","cited_by_count":4,"area":null},{"id":"2502.06556","title":"MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms","created":"2025-02-10","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":"2507.12284","title":"MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks","created":"2025-07-16","cited_by_count":4,"area":null},{"id":"2312.03042","title":"Inherent limitations of LLMs regarding spatial information","created":"2023-12-05","cited_by_count":3,"area":null},{"id":"2407.21227","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2412.08063","title":"ContextModule: Improving Code Completion via Repository-level Contextual Information","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2502.19149","title":"Isolating Language-Coding from Problem-Solving: Benchmarking LLMs with PseudoEval","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2605.07024","title":"Delulu: A Verified Multi-Lingual Benchmark for Code Hallucination Detection in Fill-in-the-Middle Tasks","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2405.14388","title":"Evaluation of the Programming Skills of Large Language Models","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2406.12635","title":"ScenEval: A Benchmark for Scenario-Based Evaluation of Code Generation","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2407.10626","title":"NoviCode: Generating Programs from Natural Language Utterances by Novices","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2409.15228","title":"A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2410.10741","title":"SensorBench: Benchmarking LLMs in Coding-Based Sensor Processing","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2411.10842","title":"CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit","created":"2024-11-16","cited_by_count":2,"area":null},{"id":"2506.08790","title":"Do Generative AI Tools Ensure Green Code? An Investigative Study","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2604.26923","title":"ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2312.10448","title":"Exploring Large Language Models in Resolving Environment-Related Crash Bugs: Localizing and Repairing","created":"2023-12-16","cited_by_count":1,"area":null},{"id":"2409.01382","title":"Automatic Detection of LLM-Generated Code: A Comparative Case Study of Contemporary Models Across Function and Class Granularities","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2409.05177","title":"Insights from Benchmarking Frontier Language Models on Web App Code Generation","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2411.17976","title":"The importance of visual modelling languages in generative software engineering","created":"2024-11-27","cited_by_count":1,"area":null},{"id":"2504.20673","title":"CoCo-Bench: A Comprehensive Code Benchmark For Multi-task Large Language Model Evaluation","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2505.14597","title":"Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2602.07079","title":"Comprehensive Evaluation of Large Language Models on Software Engineering Tasks: A Multi-Task Benchmark","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2604.10481","title":"PatchRecall: Patch-Driven Retrieval for Automated Program Repair","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2604.10520","title":"ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2408.14834","title":"Strategic Optimization and Challenges of Large Language Models in Object-Oriented Programming","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2505.21514","title":"SIMCOPILOT: Evaluating Large Language Models for Copilot-Style Code Generation","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2505.24324","title":"SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.04125","title":"Experimental Analysis of Productive Interaction Strategy with ChatGPT: User Study on Function and Project-level Code Generation Tasks","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2510.27565","title":"CodeAlignBench: Assessing Code Generation Models on Developer-Preferred Code Adjustments","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2601.21070","title":"Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering","created":"2026-01-28","cited_by_count":0,"area":null}],"next_cursor":"100"}