{"total":108,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"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":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366,"area":null},{"id":"2105.12655","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","created":"2021-05-25","cited_by_count":200,"area":null},{"id":"2403.18105","title":"Large Language Models for Education: A Survey and Outlook","created":"2024-03-26","cited_by_count":188,"area":null},{"id":"2112.02125","title":"Examining Zero-Shot Vulnerability Repair with Large Language Models","created":"2021-12-03","cited_by_count":105,"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":"2410.14684","title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","created":"2024-10-03","cited_by_count":91,"area":null},{"id":"2103.00073","title":"CURE: Code-Aware Neural Machine Translation for Automatic Program Repair","created":"2021-02-26","cited_by_count":86,"area":null},{"id":"2110.06773","title":"Leveraging Automated Unit Tests for Unsupervised Code Translation","created":"2021-10-13","cited_by_count":82,"area":null},{"id":"2102.07492","title":"DOBF: A Deobfuscation Pre-Training Objective for Programming Languages","created":"2021-02-15","cited_by_count":68,"area":null},{"id":"2212.10007","title":"CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context","created":"2022-12-20","cited_by_count":65,"area":null},{"id":"2309.00608","title":"Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair","created":"2023-09-01","cited_by_count":55,"area":null},{"id":"2206.07585","title":"NatGen: Generative pre-training by \"Naturalizing\" source code","created":"2022-06-15","cited_by_count":54,"area":null},{"id":"2206.00052","title":"CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models","created":"2022-05-31","cited_by_count":53,"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":"2308.11148","title":"LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning","created":"2023-08-22","cited_by_count":47,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2208.05446","title":"CoditT5: Pretraining for Source Code and Natural Language Editing","created":"2022-08-10","cited_by_count":45,"area":null},{"id":"2310.12418","title":"The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions","created":"2023-10-19","cited_by_count":45,"area":null},{"id":"2309.06057","title":"RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair","created":"2023-09-12","cited_by_count":44,"area":"rag"},{"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":"2104.08308","title":"Neural Transfer Learning for Repairing Security Vulnerabilities in C Code","created":"2021-04-16","cited_by_count":36,"area":null},{"id":"2401.03003","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","created":"2024-01-05","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":"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":"2306.00108","title":"Better patching using LLM prompting, via Self-Consistency","created":"2023-05-31","cited_by_count":29,"area":"lr"},{"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":"2108.06645","title":"On Multi-Modal Learning of Editing Source Code","created":"2021-08-15","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":"2306.08350","title":"Multi-target Backdoor Attacks for Code Pre-trained Models","created":"2023-06-14","cited_by_count":23,"area":"safety"},{"id":"2307.02435","title":"Exploring Continual Learning for Code Generation Models","created":"2023-07-05","cited_by_count":22,"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":"2104.07896","title":"Generating Bug-Fixes Using Pretrained Transformers","created":"2021-04-16","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":"2302.04030","title":"CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models","created":"2023-02-08","cited_by_count":16,"area":null},{"id":"2304.12015","title":"ITER: Iterative Neural Repair for Multi-Location Patches","created":"2023-04-24","cited_by_count":16,"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":"2306.03203","title":"A Static Evaluation of Code Completion by Large Language Models","created":"2023-06-05","cited_by_count":14,"area":null},{"id":"2308.12415","title":"Benchmarking Causal Study to Interpret Large Language Models for Source Code","created":"2023-08-23","cited_by_count":14,"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":"2302.01857","title":"KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair","created":"2023-02-03","cited_by_count":13,"area":null},{"id":"2108.07639","title":"Learning C to x86 Translation: An Experiment in Neural Compilation","created":"2021-08-17","cited_by_count":12,"area":null},{"id":"2302.03788","title":"Toward a Theory of Causation for Interpreting Neural Code Models","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2210.17029","title":"Poison Attack and Defense on Deep Source Code Processing Models","created":"2022-10-31","cited_by_count":11,"area":"safety"},{"id":"2304.01102","title":"RunBugRun -- An Executable Dataset for Automated Program Repair","created":"2023-04-03","cited_by_count":11,"area":null},{"id":"2212.11414","title":"Improving Automated Program Repair with Domain Adaptation","created":"2022-12-21","cited_by_count":10,"area":null},{"id":"2606.22902","title":"Agent-as-a-Router: Agentic Model Routing for Coding Tasks","created":"2026-06-22","cited_by_count":10,"area":"agents"},{"id":"2401.03855","title":"PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2204.06643","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","created":"2022-04-13","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":"2502.15830","title":"Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalness","created":"2025-02-20","cited_by_count":8,"area":"safety"},{"id":"2208.04125","title":"Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness","created":"2022-08-08","cited_by_count":7,"area":null},{"id":"2405.05455","title":"Automated Program Repair: Emerging trends pose and expose problems for benchmarks","created":"2024-05-08","cited_by_count":7,"area":null},{"id":"2401.10359","title":"Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting","created":"2024-01-18","cited_by_count":6,"area":null},{"id":"2504.19444","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2210.04802","title":"SimSCOOD: Systematic Analysis of Out-of-Distribution Generalization in Fine-tuned Source Code Models","created":"2022-10-10","cited_by_count":5,"area":null},{"id":"2309.12938","title":"Frustrated with Code Quality Issues? LLMs can Help!","created":"2023-09-22","cited_by_count":5,"area":null},{"id":"2402.11892","title":"Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing","created":"2024-02-19","cited_by_count":5,"area":null},{"id":"2407.08956","title":"Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss","created":"2024-07-12","cited_by_count":5,"area":"safety"},{"id":"2410.16655","title":"Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2207.00301","title":"Can we learn from developer mistakes? Learning to localize and repair real bugs from real bug fixes","created":"2022-07-01","cited_by_count":4,"area":null},{"id":"2404.04839","title":"AI for DevSecOps: A Landscape and Future Opportunities","created":"2024-04-07","cited_by_count":4,"area":null},{"id":"2409.10959","title":"Leveraging Reviewer Experience in Code Review Comment Generation","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2109.10476","title":"Self-Supervised Learning to Prove Equivalence Between Straight-Line Programs via Rewrite Rules","created":"2021-09-22","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":"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":"2211.06335","title":"Using Developer Discussions to Guide Fixing Bugs in Software","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2212.05773","title":"A Survey on Natural Language Processing for Programming","created":"2022-12-12","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":"2401.07518","title":"Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2401.07994","title":"Assessing the Latent Automated Program Repair Capabilities of Large Language Models using Round-Trip Translation","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2402.02627","title":"Stability Analysis of Various Symbolic Rule Extraction Methods from Recurrent Neural Network","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2508.11110","title":"Diffusion is a code repair operator and generator","created":"2025-08-14","cited_by_count":3,"area":"diffusion"},{"id":"2604.05481","title":"On the Role of Fault Localization Context for LLM-Based Program Repair","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.27238","title":"EviACT: An Evidence-to-Action Framework for Agentic Program Repair","created":"2026-05-26","cited_by_count":3,"area":"agents"},{"id":"2106.02452","title":"Proving Equivalence Between Complex Expressions Using Graph-to-Sequence Neural Models","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2212.09132","title":"JEMMA: An Extensible Java Dataset for ML4Code Applications","created":"2022-12-18","cited_by_count":2,"area":null},{"id":"2309.14760","title":"Program Repair with Minimal Edits Using CodeT5","created":"2023-09-26","cited_by_count":2,"area":null},{"id":"2410.20136","title":"CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification","created":"2024-10-26","cited_by_count":2,"area":"safety"},{"id":"2111.05827","title":"Data-Driven AI Model Signal-Awareness Enhancement and Introspection","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2201.07984","title":"AstBERT: Enabling Language Model for Financial Code Understanding with Abstract Syntax Trees","created":"2022-01-20","cited_by_count":1,"area":null},{"id":"2202.03055","title":"Enabling Automatic Repair of Source Code Vulnerabilities Using Data-Driven Methods","created":"2022-02-07","cited_by_count":1,"area":null},{"id":"2205.13342","title":"Leveraging Causal Inference for Explainable Automatic Program Repair","created":"2022-05-26","cited_by_count":1,"area":null},{"id":"2308.08943","title":"Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2406.10141","title":"The Rise and Fall(?) of Software Engineering","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2407.08890","title":"DeepCodeProbe: Towards Understanding What Models Trained on Code Learn","created":"2024-07-11","cited_by_count":1,"area":null},{"id":"2412.15948","title":"Trust Calibration in IDEs: Paving the Way for Widespread Adoption of AI Refactoring","created":"2024-12-20","cited_by_count":1,"area":null},{"id":"2502.03806","title":"Should Code Models Learn Pedagogically? A Preliminary Evaluation of Curriculum Learning for Real-World Software Engineering Tasks","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2507.10103","title":"Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models","created":"2025-07-14","cited_by_count":1,"area":"rag"},{"id":"2508.03487","title":"BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2604.11518","title":"From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to Python","created":"2026-04-13","cited_by_count":1,"area":"agents"},{"id":"2607.12605","title":"Multi-Perspective Agentic Program Repair via Code Property Graphs and Temporal Execution Graphs","created":"2026-07-14","cited_by_count":1,"area":"agents"},{"id":"2201.07674","title":"Code Sophistication: From Code Recommendation to Logic Recommendation","created":"2022-01-19","cited_by_count":0,"area":null},{"id":"2302.10812","title":"On ML-Based Program Translation: Perils and Promises","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2502.10953","title":"Empirical evaluation of LLMs in predicting fixes of Configuration bugs in Smart Home System","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2505.07372","title":"Self-Bootstrapping Automated Program Repair: Using LLMs to Generate and Evaluate Synthetic Training Data for Bug Repair","created":"2025-05-12","cited_by_count":0,"area":"synth"},{"id":"2506.21211","title":"$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models","created":"2025-06-26","cited_by_count":0,"area":"lr"},{"id":"2508.09332","title":"Teaching Code Refactoring Using LLMs","created":"2025-08-12","cited_by_count":0,"area":null}],"next_cursor":"100"}