Image de couverture de livre

LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Ziyao, Wang, Yanlin, Wang, Chong, Chen, Jiachi, Zheng, Zibin
Format:	Preprint
Publié:	2024
Sujets:	Software Engineering Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards an Understanding of Context Utilization in Code Intelligence
par: Wang, Yanlin, et autres
Publié: (2025)

Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark
par: Zheng, Dewu, et autres
Publié: (2024)

RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation
par: Wang, Yanli, et autres
Publié: (2024)

ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation
par: Liu, Sicong, et autres
Publié: (2026)

Agents in Software Engineering: Survey, Landscape, and Vision
par: Wang, Yanlin, et autres
Publié: (2024)

An Empirical Study of Agent Developer Practices in AI Agent Frameworks
par: Wang, Yanlin, et autres
Publié: (2025)

AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion
par: Jiang, Tianyue, et autres
Publié: (2026)

RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation
par: Liang, Linxi, et autres
Publié: (2025)

Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models
par: Wang, Yanlin, et autres
Publié: (2024)

CodeMirage: Hallucinations in Code Generated by Large Language Models
par: Agarwal, Vibhor, et autres
Publié: (2024)

DevEval: Evaluating Code Generation in Practical Software Projects
par: Li, Jia, et autres
Publié: (2024)

RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories
par: Wang, Yanlin, et autres
Publié: (2026)

Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code
par: He, Kaifeng, et autres
Publié: (2026)

IndustryCode: A Benchmark for Industry Code Generation
par: Zeng, Puyu, et autres
Publié: (2026)

Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code
par: Jiang, Nan, et autres
Publié: (2024)

OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
par: Zheng, Tianyu, et autres
Publié: (2024)

ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries
par: Maharaj, Kishan, et autres
Publié: (2024)

Pragmatic Reasoning improves LLM Code Generation
par: Cao, Zhuchen, et autres
Publié: (2025)

Mitigating Gender Bias in Code Large Language Models via Model Editing
par: Qin, Zhanyue, et autres
Publié: (2024)

The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation
par: Gao, Shuzheng, et autres
Publié: (2025)

Rigor, Reliability, and Reproducibility Matter: A Decade-Scale Survey of 572 Code Benchmarks
par: Cao, Jialun, et autres
Publié: (2025)

SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
par: Guo, Lianghong, et autres
Publié: (2025)

Magicoder: Empowering Code Generation with OSS-Instruct
par: Wei, Yuxiang, et autres
Publié: (2023)

LocAgent: Graph-Guided LLM Agents for Code Localization
par: Chen, Zhaoling, et autres
Publié: (2025)

UA-Code-Bench: A Competitive Programming Benchmark for Evaluating LLM Code Generation in Ukrainian
par: Syromiatnikov, Mykyta, et autres
Publié: (2025)

CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks
par: Jiang, Hongchao, et autres
Publié: (2025)

Crystal: Illuminating LLM Abilities on Language and Code
par: Tao, Tianhua, et autres
Publié: (2024)

CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
par: Yan, Weixiang, et autres
Publié: (2023)

Generating High-Quality Datasets for Code Editing via Open-Source Language Models
par: Zhang, Zekai, et autres
Publié: (2025)

A Taxonomy of Prompt Defects in LLM Systems
par: Tian, Haoye, et autres
Publié: (2025)

A Survey on Code Generation with LLM-based Agents
par: Dong, Yihong, et autres
Publié: (2025)

PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
par: Peng, Yun, et autres
Publié: (2024)

Benchmarking LLM Code Generation for Audio Programming with Visual Dataflow Languages
par: Zhang, William, et autres
Publié: (2024)

Deployability-Centric Infrastructure-as-Code Generation: Fail, Learn, Refine, and Succeed through LLM-Empowered DevOps Simulation
par: Zhang, Tianyi, et autres
Publié: (2025)

Multilingual Multimodal Software Developer for Code Generation
par: Chai, Linzheng, et autres
Publié: (2025)

Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
par: Sapkota, Ranjan, et autres
Publié: (2025)

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
par: Shi, Yuling, et autres
Publié: (2024)

Identifying Smart Contract Security Issues in Code Snippets from Stack Overflow
par: Chen, Jiachi, et autres
Publié: (2024)

Verification Limits Code LLM Training
par: Gureja, Srishti, et autres
Publié: (2025)

A Survey on Large Language Models for Code Generation
par: Jiang, Juyong, et autres
Publié: (2024)