Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Zhenyu, Sheng, Victor S.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Software Engineering Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT
di: Xu, Zhenyu, et al.
Pubblicazione: (2024)

Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation Capabilities
di: Wang, Hanbin, et al.
Pubblicazione: (2025)

NARRepair: Non-Autoregressive Code Generation Model for Automatic Program Repair
di: Yang, Zhenyu, et al.
Pubblicazione: (2024)

Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review
di: Kamalı, Hüseyin Özgür, et al.
Pubblicazione: (2026)

Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation
di: Liu, Mingwei, et al.
Pubblicazione: (2025)

Uncertainty Quantification for LLM-based Code Generation
di: Xu, Senrong, et al.
Pubblicazione: (2026)

Multi-Task Program Error Repair and Explanatory Diagnosis
di: Xu, Zhenyu, et al.
Pubblicazione: (2024)

Specification and Detection of LLM Code Smells
di: Mahmoudi, Brahim, et al.
Pubblicazione: (2025)

WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation
di: Xu, Mingde, et al.
Pubblicazione: (2025)

Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
di: Akli, Amal, et al.
Pubblicazione: (2026)

Using a Feedback Loop for LLM-based Infrastructure as Code Generation
di: Palavalli, Mayur Amarnath, et al.
Pubblicazione: (2024)

Investigating The Smells of LLM Generated Code
di: Paul, Debalina Ghosh, et al.
Pubblicazione: (2025)

Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code Rewriting
di: Ye, Tong, et al.
Pubblicazione: (2024)

Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation
di: Vartziotis, Tina, et al.
Pubblicazione: (2024)

Detecting and Correcting Hallucinations in LLM-Generated Code via Deterministic AST Analysis
di: Khati, Dipin, et al.
Pubblicazione: (2026)

Repository Intelligence Graph: Deterministic Architectural Map for LLM Code Assistants
di: Cherny-Shahar, Tsvi, et al.
Pubblicazione: (2026)

Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation
di: Tang, Xunzhu, et al.
Pubblicazione: (2025)

CodeFort: Robust Training for Code Generation Models
di: Zhang, Yuhao, et al.
Pubblicazione: (2024)

The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code
di: Ye, Hengzhi, et al.
Pubblicazione: (2026)

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs
di: He, Yicheng, et al.
Pubblicazione: (2026)

Personality-Guided Code Generation Using Large Language Models
di: Guo, Yaoqi, et al.
Pubblicazione: (2024)

ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation
di: Zhao, Yicong, et al.
Pubblicazione: (2025)

TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation
di: Xian, Zixiang, et al.
Pubblicazione: (2023)

A Performance Study of LLM-Generated Code on Leetcode
di: Coignion, Tristan, et al.
Pubblicazione: (2024)

Bias Testing and Mitigation in LLM-based Code Generation
di: Huang, Dong, et al.
Pubblicazione: (2023)

Assessing GPT-4-Vision's Capabilities in UML-Based Code Generation
di: Antal, Gábor, et al.
Pubblicazione: (2024)

CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection
di: Zhang, Qingyu, et al.
Pubblicazione: (2025)

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability
di: He, Mengliang, et al.
Pubblicazione: (2025)

Logic Error Localization in Student Programming Assignments Using Pseudocode and Graph Neural Networks
di: Xu, Zhenyu, et al.
Pubblicazione: (2024)

Model-Driven Quantum Code Generation Using Large Language Models and Retrieval-Augmented Generation
di: Siavash, Nazanin, et al.
Pubblicazione: (2025)

RedCode: Risky Code Execution and Generation Benchmark for Code Agents
di: Guo, Chengquan, et al.
Pubblicazione: (2024)

BugSpotter: Automated Generation of Code Debugging Exercises
di: Pădurean, Victor-Alexandru, et al.
Pubblicazione: (2024)

Hallucination in LLM-Based Code Generation: An Automotive Case Study
di: Pavel, Marc, et al.
Pubblicazione: (2025)

Task Abstention for Large Language Models in Code Generation
di: Zhou, Yanke, et al.
Pubblicazione: (2026)

Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
di: Liu, Fang, et al.
Pubblicazione: (2024)

Constraint Decay: The Fragility of LLM Agents in Backend Code Generation
di: Dente, Francesco, et al.
Pubblicazione: (2026)

Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback
di: He, Lehan, et al.
Pubblicazione: (2025)

Let the Code LLM Edit Itself When You Edit the Code
di: He, Zhenyu, et al.
Pubblicazione: (2024)

Large Language Model Guided Self-Debugging Code Generation
di: Adnan, Muntasir, et al.
Pubblicazione: (2025)

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