{"total":53,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"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":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124,"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":"2105.13239","title":"CoSQA: 20,000+ Web Queries for Code Search and Question Answering","created":"2021-05-27","cited_by_count":75,"area":null},{"id":"2208.03133","title":"Out of the BLEU: how should we assess quality of the Code Generation models?","created":"2022-08-05","cited_by_count":65,"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":"2412.21199","title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation","created":"2024-12-30","cited_by_count":39,"area":null},{"id":"2206.03865","title":"Fault-Aware Neural Code Rankers","created":"2022-06-04","cited_by_count":33,"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":"2109.08365","title":"CodeQA: A Question Answering Dataset for Source Code Comprehension","created":"2021-09-17","cited_by_count":30,"area":null},{"id":"2202.06649","title":"On the Importance of Building High-quality Training Datasets for Neural Code Search","created":"2022-02-14","cited_by_count":30,"area":null},{"id":"2305.15507","title":"The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python","created":"2023-05-24","cited_by_count":29,"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":"2412.17744","title":"RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation","created":"2024-12-23","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":"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":"2305.06156","title":"The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation","created":"2023-05-09","cited_by_count":20,"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":"2206.07245","title":"An Extractive-and-Abstractive Framework for Source Code Summarization","created":"2022-06-15","cited_by_count":18,"area":null},{"id":"2601.00376","title":"In Line with Context: Repository-Level Code Generation via Context Inlining","created":"2026-01-01","cited_by_count":18,"area":null},{"id":"2212.09885","title":"Python Code Generation by Asking Clarification Questions","created":"2022-12-19","cited_by_count":17,"area":null},{"id":"2202.06521","title":"Source Code Summarization with Structural Relative Position Guided Transformer","created":"2022-02-14","cited_by_count":14,"area":null},{"id":"2203.09707","title":"M2TS: Multi-Scale Multi-Modal Approach Based on Transformer for Source Code Summarization","created":"2022-03-18","cited_by_count":14,"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":"2210.08332","title":"Code Recommendation for Open Source Software Developers","created":"2022-10-15","cited_by_count":13,"area":null},{"id":"2412.00726","title":"Free and Customizable Code Documentation with LLMs: A Fine-Tuning Approach","created":"2024-12-01","cited_by_count":10,"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":"2411.03012","title":"Leveraging Large Language Models in Code Question Answering: Baselines and Issues","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2103.03457","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","created":"2021-03-05","cited_by_count":5,"area":null},{"id":"2103.11448","title":"Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach","created":"2021-03-21","cited_by_count":5,"area":null},{"id":"2108.05198","title":"Natural Language-Guided Programming","created":"2021-08-11","cited_by_count":4,"area":null},{"id":"2211.15395","title":"CodeExp: Explanatory Code Document Generation","created":"2022-11-25","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":"2108.10763","title":"ComSum: Commit Messages Summarization and Meaning Preservation","created":"2021-08-23","cited_by_count":3,"area":null},{"id":"2111.08874","title":"GN-Transformer: Fusing Sequence and Graph Representation for Improved Code Summarization","created":"2021-11-17","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":"2209.06634","title":"Automatic Comment Generation via Multi-Pass Deliberation","created":"2022-09-14","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":"2410.16292","title":"An evaluation of LLM code generation capabilities through graded exercises","created":"2024-10-06","cited_by_count":3,"area":null},{"id":"2112.11858","title":"End to End Software Engineering Research","created":"2021-12-22","cited_by_count":2,"area":null},{"id":"2201.08810","title":"GAP-Gen: Guided Automatic Python Code Generation","created":"2022-01-19","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":"2112.00663","title":"Graph Conditioned Sparse-Attention for Improved Source Code Understanding","created":"2021-12-01","cited_by_count":1,"area":null},{"id":"2505.09062","title":"Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2106.06090","title":"Graph Neural Networks for Natural Language Processing: A Survey","created":"2021-06-10","cited_by_count":0,"area":null},{"id":"2311.06453","title":"DocGen: Generating Detailed Parameter Docstrings in Python","created":"2023-11-11","cited_by_count":0,"area":null},{"id":"2312.01921","title":"A Machine Learning Approach Towards SKILL Code Autocompletion","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2312.15152","title":"Data Classification With Multiprocessing","created":"2023-12-23","cited_by_count":0,"area":null},{"id":"2406.13877","title":"A Systematic Literature Review on the Use of Machine Learning in Software Engineering","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2503.01098","title":"Towards Automated Smart Contract Generation: Evaluation, Benchmarking, and Retrieval-Augmented Repair","created":"2025-03-03","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}],"next_cursor":null}