{"total":126,"rows":[{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462,"area":"lr"},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763,"area":null},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714,"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":"2202.13169","title":"A Systematic Evaluation of Large Language Models of Code","created":"2022-02-26","cited_by_count":363,"area":null},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359,"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":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174,"area":null},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"id":"2403.18624","title":"Vulnerability Detection with Code Language Models: How Far Are We?","created":"2024-03-27","cited_by_count":139,"area":null},{"id":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112,"area":null},{"id":"2206.12839","title":"Repository-Level Prompt Generation for Large Language Models of Code","created":"2022-06-26","cited_by_count":106,"area":null},{"id":"2006.05405","title":"Retrieval-Augmented Generation for Code Summarization via Hybrid GNN","created":"2020-06-09","cited_by_count":89,"area":"rag"},{"id":"2304.06815","title":"Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)","created":"2023-04-13","cited_by_count":72,"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":"2312.17120","title":"MathPile: A Billion-Token-Scale Pretraining Corpus for Math","created":"2023-12-28","cited_by_count":67,"area":null},{"id":"2403.04811","title":"Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models","created":"2024-03-06","cited_by_count":65,"area":null},{"id":"2105.12787","title":"Self-Supervised Bug Detection and Repair","created":"2021-05-26","cited_by_count":59,"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":"2202.06689","title":"CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences","created":"2022-02-14","cited_by_count":50,"area":null},{"id":"2107.07112","title":"On the Evaluation of Neural Code Summarization","created":"2021-07-15","cited_by_count":48,"area":null},{"id":"2303.11455","title":"Large Language Models and Simple, Stupid Bugs","created":"2023-03-20","cited_by_count":45,"area":null},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2112.02043","title":"Multilingual training for Software Engineering","created":"2021-12-03","cited_by_count":43,"area":null},{"id":"2402.16197","title":"Language Models for Code Completion: A Practical Evaluation","created":"2024-02-25","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":"2302.01973","title":"Measuring The Impact Of Programming Language Distribution","created":"2023-02-03","cited_by_count":32,"area":null},{"id":"2407.07959","title":"Source Code Summarization in the Era of Large Language Models","created":"2024-07-09","cited_by_count":31,"area":null},{"id":"2104.09340","title":"Code Structure Guided Transformer for Source Code Summarization","created":"2021-04-19","cited_by_count":30,"area":null},{"id":"2310.01602","title":"CAT-LM: Training Language Models on Aligned Code And Tests","created":"2023-10-02","cited_by_count":28,"area":null},{"id":"2301.01701","title":"Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries","created":"2023-01-04","cited_by_count":26,"area":null},{"id":"2505.11413","title":"CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs","created":"2025-05-16","cited_by_count":26,"area":"safety"},{"id":"2103.11599","title":"Project-Level Encoding for Neural Source Code Summarization of Subroutines","created":"2021-03-22","cited_by_count":24,"area":null},{"id":"2106.10158","title":"Learning to Complete Code with Sketches","created":"2021-06-18","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":"2101.04470","title":"Type4Py: Practical Deep Similarity Learning-Based Type Inference for Python","created":"2021-01-12","cited_by_count":19,"area":null},{"id":"2106.08704","title":"Memorization and Generalization in Neural Code Intelligence Models","created":"2021-06-16","cited_by_count":19,"area":null},{"id":"2212.08108","title":"Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detection","created":"2022-12-15","cited_by_count":19,"area":null},{"id":"2401.16448","title":"LLM4SecHW: Leveraging Domain Specific Large Language Model for Hardware Debugging","created":"2024-01-28","cited_by_count":18,"area":null},{"id":"2210.04261","title":"Noise-Robust De-Duplication at Scale","created":"2022-10-09","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":"2305.14129","title":"GrACE: Generation using Associated Code Edits","created":"2023-05-23","cited_by_count":16,"area":null},{"id":"2308.13490","title":"TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs","created":"2023-08-25","cited_by_count":16,"area":null},{"id":"2204.10049","title":"On Distribution Shift in Learning-based Bug Detectors","created":"2022-04-21","cited_by_count":15,"area":null},{"id":"2301.13779","title":"FLAME: A small language model for spreadsheet formulas","created":"2023-01-31","cited_by_count":15,"area":null},{"id":"2210.16494","title":"Aligning Offline Metrics and Human Judgments of Value for Code Generation Models","created":"2022-10-29","cited_by_count":14,"area":null},{"id":"2212.02684","title":"Codex Hacks HackerRank: Memorization Issues and a Framework for Code Synthesis Evaluation","created":"2022-12-06","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":"2309.09826","title":"Efficient Avoidance of Vulnerabilities in Auto-completed Smart Contract Code Using Vulnerability-constrained Decoding","created":"2023-09-18","cited_by_count":14,"area":null},{"id":"2310.08069","title":"Rethinking Negative Pairs in Code Search","created":"2023-10-12","cited_by_count":14,"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":"2303.09564","title":"TypeT5: Seq2seq Type Inference using Static Analysis","created":"2023-03-16","cited_by_count":12,"area":null},{"id":"2407.06654","title":"SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2410.04715","title":"Selection of LLM Fine-Tuning Data based on Orthogonal Rules","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2108.09619","title":"Impact of Evaluation Methodologies on Code Summarization","created":"2021-08-22","cited_by_count":11,"area":null},{"id":"2306.17281","title":"HPC-Coder: Modeling Parallel Programs using Large Language Models","created":"2023-06-29","cited_by_count":11,"area":null},{"id":"2304.13840","title":"A Deep Learning Framework for Verilog Autocompletion Towards Design and Verification Automation","created":"2023-04-26","cited_by_count":10,"area":null},{"id":"2405.15523","title":"The Mosaic Memory of Large Language Models","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2104.04706","title":"ManyTypes4Py: A Benchmark Python Dataset for Machine Learning-based Type Inference","created":"2021-04-10","cited_by_count":9,"area":null},{"id":"2211.05239","title":"RecD: Deduplication for End-to-End Deep Learning Recommendation Model Training Infrastructure","created":"2022-11-09","cited_by_count":9,"area":null},{"id":"2305.12322","title":"Learning Large Graph Property Prediction via Graph Segment Training","created":"2023-05-21","cited_by_count":9,"area":null},{"id":"2308.03873","title":"Evaluating and Explaining Large Language Models for Code Using Syntactic Structures","created":"2023-08-07","cited_by_count":9,"area":null},{"id":"2304.12269","title":"Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2305.09773","title":"Towards Modeling Human Attention from Eye Movements for Neural Source Code Summarization","created":"2023-05-16","cited_by_count":8,"area":null},{"id":"2403.05188","title":"CommitBench: A Benchmark for Commit Message Generation","created":"2024-03-08","cited_by_count":8,"area":null},{"id":"2407.01646","title":"ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization","created":"2024-07-01","cited_by_count":8,"area":null},{"id":"2411.06221","title":"Smart-LLaMA: Two-Stage Post-Training of Large Language Models for Smart Contract Vulnerability Detection and Explanation","created":"2024-11-09","cited_by_count":8,"area":null},{"id":"2205.14374","title":"Syntax-Guided Program Reduction for Understanding Neural Code Intelligence Models","created":"2022-05-28","cited_by_count":7,"area":null},{"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":"2210.09597","title":"Soft-Labeled Contrastive Pre-training for Function-level Code Representation","created":"2022-10-18","cited_by_count":7,"area":null},{"id":"2212.03978","title":"Learning Graph Search Heuristics","created":"2022-12-07","cited_by_count":7,"area":"offlinerl"},{"id":"2305.04106","title":"On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2403.15185","title":"Investigating the Performance of Language Models for Completing Code in Functional Programming Languages: a Haskell Case Study","created":"2024-03-22","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":"2506.18245","title":"Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection","created":"2025-06-23","cited_by_count":7,"area":"alignment"},{"id":"2105.05991","title":"Improving Code Autocompletion with Transfer Learning","created":"2021-05-12","cited_by_count":6,"area":null},{"id":"2206.13619","title":"DeepPERF: A Deep Learning-Based Approach For Improving Software Performance","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2208.08100","title":"CommitBART: A Large Pre-trained Model for GitHub Commits","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2501.09653","title":"The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models","created":"2025-01-16","cited_by_count":6,"area":null},{"id":"2206.00804","title":"Learning code summarization from a small and local dataset","created":"2022-06-02","cited_by_count":5,"area":null},{"id":"2306.12550","title":"On Evaluation of Document Classification using RVL-CDIP","created":"2023-06-21","cited_by_count":5,"area":null},{"id":"2308.07429","title":"Semantic Similarity Loss for Neural Source Code Summarization","created":"2023-08-14","cited_by_count":5,"area":null},{"id":"2311.00931","title":"Learning Defect Prediction from Unrealistic Data","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2402.14482","title":"SpanSeq: Similarity-based sequence data splitting method for improved development and assessment of deep learning projects","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2111.01097","title":"Code2Snapshot: Using Code Snapshots for Learning Representations of Source Code","created":"2021-11-01","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":"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":"2405.11466","title":"Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code","created":"2024-05-19","cited_by_count":4,"area":"safety"},{"id":"2410.21346","title":"Towards Trustworthy Machine Learning in Production: An Overview of the Robustness in MLOps Approach","created":"2024-10-28","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":"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":"2306.11943","title":"Towards Understanding What Code Language Models Learned","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2309.02326","title":"Revisiting File Context for Source Code Summarization","created":"2023-09-05","cited_by_count":3,"area":null},{"id":"2311.17259","title":"SoUnD Framework: Analyzing (So)cial Representation in (Un)structured (D)ata","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2410.07573","title":"RealVul: Can We Detect Vulnerabilities in Web Applications with LLM?","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2508.17361","title":"Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias","created":"2025-08-24","cited_by_count":3,"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":"2303.01739","title":"Study of Distractors in Neural Models of Code","created":"2023-03-03","cited_by_count":2,"area":null}],"next_cursor":"100"}