{"total":43,"rows":[{"id":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300,"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":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159,"area":null},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138,"area":null},{"id":"2301.13816","title":"Execution-based Code Generation using Deep Reinforcement Learning","created":"2023-01-31","cited_by_count":99,"area":null},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57,"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":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46,"area":null},{"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":"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":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30,"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":"2406.07411","title":"VersiCode: Towards Version-controllable Code Generation","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2506.19004","title":"Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations","created":"2025-06-23","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":"2403.17214","title":"Output Format Biases in the Evaluation of Large Language Models for Code Translation","created":"2024-03-25","cited_by_count":9,"area":null},{"id":"2507.19598","title":"MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2306.09308","title":"Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2504.10557","title":"The Code Barrier: What LLMs Actually Understand?","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2506.01074","title":"How Programming Concepts and Neurons Are Shared in Code Language Models","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2310.16803","title":"Language Agnostic Code Embeddings","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2401.08089","title":"A Study on Training and Developing Large Language Models for Behavior Tree Generation","created":"2024-01-16","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":"2504.00019","title":"ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2507.11083","title":"Function-to-Style Guidance of LLMs for Code Translation","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2308.13754","title":"ZC3: Zero-Shot Cross-Language Code Clone Detection","created":"2023-08-26","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":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2512.07666","title":"Bridging Code Graphs and Large Language Models for Better Code Understanding","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2604.25960","title":"Large Language Models for Multilingual Code Intelligence: A Survey","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2310.14209","title":"SUT: Active Defects Probing for Transcompiler Models","created":"2023-10-22","cited_by_count":1,"area":null},{"id":"2405.04126","title":"Refining Joint Text and Source Code Embeddings for Retrieval Task with Parameter-Efficient Fine-Tuning","created":"2024-05-07","cited_by_count":1,"area":null},{"id":"2409.05177","title":"Insights from Benchmarking Frontier Language Models on Web App Code Generation","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2503.11237","title":"Collaboration is all you need: LLM Assisted Safe Code Translation","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2312.12492","title":"CodeLL: A Lifelong Learning Dataset to Support the Co-Evolution of Data and Language Models of Code","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2404.01754","title":"Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2404.19631","title":"On Training a Neural Network to Explain Binaries","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2410.18107","title":"In-Context Code-Text Learning for Bimodal Software Engineering","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2503.05315","title":"LoRACode: LoRA Adapters for Code Embeddings","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2510.15004","title":"Automated Snippet-Alignment Data Augmentation for Code Translation","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2512.18456","title":"SoK: Understanding (New) Security Issues Across AI4Code Use Cases","created":"2025-12-20","cited_by_count":0,"area":null}],"next_cursor":null}