{"total":35,"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":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"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":"2406.01304","title":"CodeR: Issue Resolving with Multi-Agent and Task Graphs","created":"2024-06-03","cited_by_count":91,"area":null},{"id":"2405.04760","title":"Large Language Models for Cyber Security: A Systematic Literature Review","created":"2024-05-08","cited_by_count":68,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2406.08587","title":"CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery","created":"2024-06-12","cited_by_count":30,"area":null},{"id":"2405.11966","title":"Multiple-Choice Questions are Efficient and Robust LLM Evaluators","created":"2024-05-20","cited_by_count":28,"area":null},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27,"area":null},{"id":"2406.10303","title":"A Survey on Large Language Models from General Purpose to Medical Applications: Datasets, Methodologies, and Evaluations","created":"2024-06-14","cited_by_count":16,"area":null},{"id":"2503.24260","title":"MaintainCoder: Maintainable Code Generation Under Dynamic Requirements","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2402.09136","title":"DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2408.05506","title":"Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers","created":"2024-08-10","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":"2408.04820","title":"Natural Language Outlines for Code: Literate Programming in the LLM Era","created":"2024-08-09","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":"2405.03998","title":"Sketch Then Generate: Providing Incremental User Feedback and Guiding LLM Code Generation through Language-Oriented Code Sketches","created":"2024-05-07","cited_by_count":7,"area":null},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2408.01050","title":"The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines","created":"2024-08-02","cited_by_count":5,"area":null},{"id":"2408.13372","title":"Understanding Defects in Generated Codes by Language Models","created":"2024-08-23","cited_by_count":5,"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":"2507.23121","title":"Uncovering the Fragility of Trustworthy LLMs through Chinese Textual Ambiguity","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2504.20406","title":"Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs","created":"2025-04-29","cited_by_count":3,"area":null},{"id":"2512.21332","title":"C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2603.26567","title":"Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering","created":"2026-03-27","cited_by_count":3,"area":null},{"id":"2404.09249","title":"Test Code Generation for Telecom Software Systems using Two-Stage Generative Model","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2405.10243","title":"DocuMint: Docstring Generation for Python using Small Language Models","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2409.06416","title":"Exploring the Integration of Large Language Models in Industrial Test Maintenance Processes","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2604.24814","title":"SWE-QA: A Dataset and Benchmark for Complex Code Understanding","created":"2026-04-27","cited_by_count":2,"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":"2605.04615","title":"Beyond Retrieval: A Multitask Benchmark and Model for Code Search","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2312.10750","title":"Distinguishing Translations by Human, NMT, and ChatGPT: A Linguistic and Statistical Approach","created":"2023-12-17","cited_by_count":0,"area":null},{"id":"2401.05176","title":"Convergences and Divergences between Automatic Assessment and Human Evaluation: Insights from Comparing ChatGPT-Generated Translation and Neural Machine Translation","created":"2024-01-10","cited_by_count":0,"area":null},{"id":"2407.19772","title":"Generating Unseen Code Tests In Infinitum","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2510.17591","title":"HGAdapter: Hypergraph-based Adapters in Language Models for Code Summarization and Clone Detection","created":"2025-10-20","cited_by_count":0,"area":null}],"next_cursor":null}