{"total":81,"rows":[{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"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":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183,"area":null},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117,"area":null},{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64,"area":null},{"id":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53,"area":null},{"id":"2407.21579","title":"A Performance Study of LLM-Generated Code on Leetcode","created":"2024-07-31","cited_by_count":49,"area":null},{"id":"2302.01973","title":"Measuring The Impact Of Programming Language Distribution","created":"2023-02-03","cited_by_count":32,"area":null},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"area":null},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","cited_by_count":30,"area":null},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","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":"2401.00788","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","created":"2024-01-01","cited_by_count":23,"area":null},{"id":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23,"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":"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":"2402.05980","title":"Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2408.11081","title":"What can Large Language Models Capture about Code Functional Equivalence?","created":"2024-08-20","cited_by_count":14,"area":null},{"id":"2504.00694","title":"On Benchmarking Code LLMs for Android Malware Analysis","created":"2025-04-01","cited_by_count":13,"area":null},{"id":"2506.01317","title":"T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning","created":"2025-06-02","cited_by_count":13,"area":null},{"id":"2403.08429","title":"Software Vulnerability and Functionality Assessment using LLMs","created":"2024-03-13","cited_by_count":11,"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":"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":"2308.03312","title":"Exploiting Code Symmetries for Learning Program Semantics","created":"2023-08-07","cited_by_count":10,"area":null},{"id":"2310.00749","title":"SEED: Domain-Specific Data Curation With Large Language Models","created":"2023-10-01","cited_by_count":10,"area":null},{"id":"2310.07958","title":"Towards Causal Deep Learning for Vulnerability Detection","created":"2023-10-12","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":"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":"2403.08688","title":"Token Alignment via Character Matching for Subword Completion","created":"2024-03-13","cited_by_count":9,"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":"2503.02296","title":"Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2505.10443","title":"Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?","created":"2025-05-15","cited_by_count":7,"area":null},{"id":"2509.25257","title":"RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval","created":"2025-09-27","cited_by_count":7,"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":"2410.15490","title":"Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidence","created":"2024-10-20","cited_by_count":5,"area":null},{"id":"2503.22851","title":"RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2504.13515","title":"Large Language Models for Validating Network Protocol Parsers","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2405.01567","title":"CodeFort: Robust Training for Code Generation Models","created":"2024-04-11","cited_by_count":4,"area":null},{"id":"2503.14281","title":"XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants","created":"2025-03-18","cited_by_count":4,"area":null},{"id":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2504.15284","title":"EditLord: Learning Code Transformation Rules for Code Editing","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2509.16749","title":"Evaluating LLM Generated Detection Rules in Cybersecurity","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2510.03178","title":"When Names Disappear: Revealing What LLMs Actually Understand About Code","created":"2025-10-03","cited_by_count":4,"area":null},{"id":"2510.07740","title":"AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2306.05079","title":"Enhancing Robustness of AI Offensive Code Generators via Data Augmentation","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2309.12813","title":"Automatically Testing Functional Properties of Code Translation Models","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2311.06647","title":"Robust Text Classification: Analyzing Prototype-Based Networks","created":"2023-11-11","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":"2409.13551","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2508.07180","title":"Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2508.16131","title":"The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2605.26177","title":"RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2403.10575","title":"Exploring Language Model's Code Generation Ability with Auxiliary Functions","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2404.07135","title":"Towards Robustness of Text-to-Visualization Translation against Lexical and Phrasal Variability","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2508.08332","title":"Energy-Aware Code Generation with LLMs: Benchmarking Small vs. Large Language Models for Sustainable AI Programming","created":"2025-08-10","cited_by_count":2,"area":null},{"id":"2603.23443","title":"Evaluating LLM-Based Test Generation Under Software Evolution","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2604.24703","title":"Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2605.29737","title":"Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs","created":"2026-05-28","cited_by_count":2,"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":"2510.18895","title":"CosmoCore Affective Dream-Replay Reinforcement Learning for Code Generation","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.06042","title":"Auto-SPT: Automating Semantic Preserving Transformations for Code","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2605.05267","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2608.08266","title":"On the Robustness of LLMs' Internal Representation of Code Correctness","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2608.18900","title":"TestifAI: Tomography-Based Testing for Deep Learning Systems","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2408.09568","title":"MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair","created":"2024-08-18","cited_by_count":0,"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":"2501.03783","title":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2506.02791","title":"Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2511.18488","title":"Evaluating perturbation robustness of generative systems that use COBOL code inputs","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.02567","title":"Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System","created":"2025-12-02","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},{"id":"2603.13640","title":"SemRep: Generative Code Representation Learning with Code Transformations","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2605.27981","title":"STAB: Specification-driven Testing for Algorithmic Bottlenecks","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.18642","title":"Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.12771","title":"Memorization Diagnostics for Code LLMs Should be Scale-Aware","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.19882","title":"TESTNAV: Pareto-Guided Search for Compositional Robustness Testing","created":"2026-08-20","cited_by_count":0,"area":null}],"next_cursor":null}