Image de couverture de livre

CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Zhenyu, Sheng, Victor S.
Format:	Preprint
Publié:	2025
Sujets:	Software Engineering Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT
par: Xu, Zhenyu, et autres
Publié: (2024)

Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities
par: Wang, Hanbin, et autres
Publié: (2025)

NARRepair: Non-Autoregressive Code Generation Model for Automatic Program Repair
par: Yang, Zhenyu, et autres
Publié: (2024)

Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review
par: Kamalı, Hüseyin Özgür, et autres
Publié: (2026)

Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation
par: Liu, Mingwei, et autres
Publié: (2025)

Uncertainty Quantification for LLM-based Code Generation
par: Xu, Senrong, et autres
Publié: (2026)

Multi-Task Program Error Repair and Explanatory Diagnosis
par: Xu, Zhenyu, et autres
Publié: (2024)

Specification and Detection of LLM Code Smells
par: Mahmoudi, Brahim, et autres
Publié: (2025)

WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation
par: Xu, Mingde, et autres
Publié: (2025)

Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
par: Akli, Amal, et autres
Publié: (2026)

Using a Feedback Loop for LLM-based Infrastructure as Code Generation
par: Palavalli, Mayur Amarnath, et autres
Publié: (2024)

Investigating The Smells of LLM Generated Code
par: Paul, Debalina Ghosh, et autres
Publié: (2025)

Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting
par: Ye, Tong, et autres
Publié: (2024)

Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation
par: Vartziotis, Tina, et autres
Publié: (2024)

Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis
par: Khati, Dipin, et autres
Publié: (2026)

Repository Intelligence Graph: Deterministic Architectural Map for LLM Code Assistants
par: Cherny-Shahar, Tsvi, et autres
Publié: (2026)

Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation
par: Tang, Xunzhu, et autres
Publié: (2025)

CodeFort: Robust Training for Code Generation Models
par: Zhang, Yuhao, et autres
Publié: (2024)

The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code
par: Ye, Hengzhi, et autres
Publié: (2026)

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs
par: He, Yicheng, et autres
Publié: (2026)

Personality-Guided Code Generation Using Large Language Models
par: Guo, Yaoqi, et autres
Publié: (2024)

ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation
par: Zhao, Yicong, et autres
Publié: (2025)

TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation
par: Xian, Zixiang, et autres
Publié: (2023)

A Performance Study of LLM-Generated Code on Leetcode
par: Coignion, Tristan, et autres
Publié: (2024)

Bias Testing and Mitigation in LLM-based Code Generation
par: Huang, Dong, et autres
Publié: (2023)

Assessing GPT-4-Vision's Capabilities in UML-Based Code Generation
par: Antal, Gábor, et autres
Publié: (2024)

CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection
par: Zhang, Qingyu, et autres
Publié: (2025)

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability
par: He, Mengliang, et autres
Publié: (2025)

Logic Error Localization in Student Programming Assignments Using Pseudocode and Graph Neural Networks
par: Xu, Zhenyu, et autres
Publié: (2024)

Model-Driven Quantum Code Generation Using Large Language Models and Retrieval-Augmented Generation
par: Siavash, Nazanin, et autres
Publié: (2025)

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
par: Guo, Chengquan, et autres
Publié: (2024)

BugSpotter: Automated Generation of Code Debugging Exercises
par: Pădurean, Victor-Alexandru, et autres
Publié: (2024)

Hallucination in LLM-Based Code Generation: An Automotive Case Study
par: Pavel, Marc, et autres
Publié: (2025)

Task Abstention for Large Language Models in Code Generation
par: Zhou, Yanke, et autres
Publié: (2026)

Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
par: Liu, Fang, et autres
Publié: (2024)

Constraint Decay: The Fragility of LLM Agents in Backend Code Generation
par: Dente, Francesco, et autres
Publié: (2026)

Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
par: He, Lehan, et autres
Publié: (2025)

Let the Code LLM Edit Itself When You Edit the Code
par: He, Zhenyu, et autres
Publié: (2024)

Large Language Model Guided Self-Debugging Code Generation
par: Adnan, Muntasir, et autres
Publié: (2025)

DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent Execution Traces Using LLMs to Detect Android Behavioural Code Smells
par: Cherief, Houcine Abdelkader, et autres
Publié: (2026)