{"total":59,"rows":[{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159,"area":null},{"id":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117,"area":null},{"id":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"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":"2206.08474","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","created":"2022-06-16","cited_by_count":56,"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":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","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":"2412.02883","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","created":"2024-12-03","cited_by_count":34,"area":null},{"id":"2402.09664","title":"CodeMind: Evaluating Large Language Models for Code Reasoning","created":"2024-02-15","cited_by_count":32,"area":"lr"},{"id":"2408.13001","title":"CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","created":"2024-08-23","cited_by_count":31,"area":"lr"},{"id":"2405.15189","title":"EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization","created":"2024-05-24","cited_by_count":30,"area":null},{"id":"2305.12520","title":"SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly","created":"2023-05-21","cited_by_count":28,"area":null},{"id":"2410.24117","title":"AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation","created":"2024-10-31","cited_by_count":28,"area":null},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2202.08975","title":"Probing Pretrained Models of Source Code","created":"2022-02-16","cited_by_count":26,"area":null},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","cited_by_count":26,"area":null},{"id":"2404.03543","title":"CodeEditorBench: Evaluating Code Editing Capability of Large Language Models","created":"2024-04-04","cited_by_count":23,"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":"2306.06755","title":"CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution","created":"2023-06-11","cited_by_count":22,"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":"2407.07472","title":"Rectifier: Code Translation with Corrector via LLMs","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2405.20092","title":"Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation","created":"2024-05-30","cited_by_count":19,"area":null},{"id":"2206.07796","title":"FixEval: Execution-based Evaluation of Program Fixes for Programming Problems","created":"2022-06-15","cited_by_count":17,"area":null},{"id":"2406.07411","title":"VersiCode: Towards Version-controllable Code Generation","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2410.10209","title":"EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2602.01785","title":"Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding","created":"2026-02-02","cited_by_count":13,"area":"mllm"},{"id":"2205.11116","title":"Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2503.12029","title":"Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks","created":"2025-03-15","cited_by_count":11,"area":"agents"},{"id":"2412.05829","title":"SABER: Model-agnostic Backdoor Attack on Chain-of-Thought in Neural Code Generation","created":"2024-12-08","cited_by_count":10,"area":"lr"},{"id":"2308.00683","title":"CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code","created":"2023-08-01","cited_by_count":9,"area":null},{"id":"2311.00317","title":"Data Augmentation for Code Translation with Comparable Corpora and Multiple References","created":"2023-11-01","cited_by_count":9,"area":null},{"id":"2409.19894","title":"TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment","created":"2024-09-30","cited_by_count":7,"area":null},{"id":"2501.18482","title":"A Tool for In-depth Analysis of Code Execution Reasoning of Large Language Models","created":"2025-01-30","cited_by_count":7,"area":"lr"},{"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":"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":"2507.11083","title":"Function-to-Style Guidance of LLMs for Code Translation","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2401.10716","title":"Structured Code Representations Enable Data-Efficient Adaptation of Code Language Models","created":"2024-01-19","cited_by_count":3,"area":null},{"id":"2501.16050","title":"Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2503.22776","title":"Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation","created":"2025-03-28","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":"2512.14917","title":"Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings","created":"2025-12-16","cited_by_count":3,"area":"lr"},{"id":"2510.14972","title":"TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2110.05423","title":"Using Document Similarity Methods to create Parallel Datasets for Code Translation","created":"2021-10-11","cited_by_count":1,"area":null},{"id":"2310.14209","title":"SUT: Active Defects Probing for Transcompiler Models","created":"2023-10-22","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":"2512.06902","title":"BabelCoder: Agentic Code Translation with Specification Alignment","created":"2025-12-07","cited_by_count":1,"area":"agents"},{"id":"2604.18027","title":"CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora","created":"2026-04-20","cited_by_count":1,"area":"synth"},{"id":"2111.10974","title":"Many Heads but One Brain: Fusion Brain -- a Competition and a Single Multimodal Multitask Architecture","created":"2021-11-22","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},{"id":"2510.09045","title":"LLM Based Long Code Translation using Identifier Replacement","created":"2025-10-10","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},{"id":"2601.02045","title":"The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2601.16661","title":"Revisiting the Role of Natural Language Code Comments in Code Translation","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2603.14501","title":"CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language","created":"2026-03-15","cited_by_count":0,"area":null}],"next_cursor":null}