Copertina

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	He, Yicheng, Zhao, Zheng, Kaiyu, Zhou, Dai, Bryan, Fu, Jie, Yang, Yonghui
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Software Engineering Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Code Fingerprints: Disentangled Attribution of LLM-Generated Code
di: Guo, Jiaxun, et al.
Pubblicazione: (2026)

Inferring Code Correctness from Specification
di: Florian, Tambon, et al.
Pubblicazione: (2026)

Assessing Correctness in LLM-Based Code Generation via Uncertainty Estimation
di: Sharma, Arindam, et al.
Pubblicazione: (2025)

Reducing Hallucinations in LLM-Generated Code via Semantic Triangulation
di: Dai, Yihan, et al.
Pubblicazione: (2025)

Beyond Code Generation: Assessing Code LLM Maturity with Postconditions
di: He, Fusen, et al.
Pubblicazione: (2024)

Structured Safety Auditing for Balancing Code Correctness and Content Safety in LLM-Generated Code
di: Tan, Honghao, et al.
Pubblicazione: (2026)

Towards Better Correctness and Efficiency in Code Generation
di: Feng, Yunlong, et al.
Pubblicazione: (2025)

Inducing Vulnerable Code Generation in LLM Coding Assistants
di: Zeng, Binqi, et al.
Pubblicazione: (2025)

GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation
di: Li, Jia, et al.
Pubblicazione: (2025)

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

Model-Agnostic Correctness Assessment for LLM-Generated Code via Dynamic Internal Representation Selection
di: Vu, Thanh Trong, et al.
Pubblicazione: (2025)

Statically Inferring Usage Bounds for Infrastructure as Code
di: Qiao, Feitong, et al.
Pubblicazione: (2024)

CKGFuzzer: LLM-Based Fuzz Driver Generation Enhanced By Code Knowledge Graph
di: Xu, Hanxiang, et al.
Pubblicazione: (2024)

Evaluating Efficiency and Novelty of LLM-Generated Code for Graph Analysis
di: Nia, Atieh Barati, et al.
Pubblicazione: (2025)

CodeScore-R: An Automated Robustness Metric for Assessing the FunctionalCorrectness of Code Synthesis
di: Yang, Guang, et al.
Pubblicazione: (2024)

Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification
di: Li, Zenan, et al.
Pubblicazione: (2026)

From Mirage to Grounding: Towards Reliable Multimodal Circuit-to-Verilog Code Generation
di: Yang, Guang, et al.
Pubblicazione: (2026)

LLMSniffer: Detecting LLM-Generated Code via GraphCodeBERT and Supervised Contrastive Learning
di: Dihan, Mahir Labib, et al.
Pubblicazione: (2026)

SemGuard: Real-Time Semantic Evaluator for Correcting LLM-Generated Code
di: Wang, Qinglin, et al.
Pubblicazione: (2025)

Optimal Circuit Synthesis of Linear Codes for Error Detection and Correction
di: Yang, Xi, et al.
Pubblicazione: (2026)

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

Static Analysis as a Feedback Loop: Enhancing LLM-Generated Code Beyond Correctness
di: Blyth, Scott, et al.
Pubblicazione: (2025)

QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration
di: Hu, Junze, et al.
Pubblicazione: (2025)

Prompt Optimization for LLM Code Generation via Reinforcement Learning
di: Esfahani, Ali Mohammadi, et al.
Pubblicazione: (2026)

When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
di: AKLI, Amal, et al.
Pubblicazione: (2026)

CodeArena: A Collective Evaluation Platform for LLM Code Generation
di: Du, Mingzhe, et al.
Pubblicazione: (2025)

Using Semantic Distance to Estimate Uncertainty in LLM-Based Code Generation
di: He, Weilin, et al.
Pubblicazione: (2026)

Explaining Code Risk in OSS: Towards LLM-Generated Fault Prediction Interpretations
di: Adejumo, Elijah Kayode, et al.
Pubblicazione: (2025)

GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model
di: Liu, Wei, et al.
Pubblicazione: (2024)

An Empirical Study of Interaction Smells in Multi-Turn Human-LLM Collaborative Code Generation
di: Zhang, Binquan, et al.
Pubblicazione: (2026)

Comment Traps: How Defective Commented-out Code Augment Defects in AI-Assisted Code Generation
di: Huang, Yuan, et al.
Pubblicazione: (2025)

A Multi-Language Perspective on the Robustness of LLM Code Generation
di: Rabbi, Fazle, et al.
Pubblicazione: (2025)

Automatically Recommend Code Updates: Are We There Yet?
di: Liu, Yue, et al.
Pubblicazione: (2022)

HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent
di: Wu, Jie JW, et al.
Pubblicazione: (2024)

One Size Does Not Fit All: Investigating Efficacy of Perplexity in Detecting LLM-Generated Code
di: Xu, Jinwei, et al.
Pubblicazione: (2024)

Is LLM-Generated Code More Maintainable \& Reliable than Human-Written Code?
di: Molison, Alfred Santa, et al.
Pubblicazione: (2025)

BitsAI-CR: Automated Code Review via LLM in Practice
di: Sun, Tao, et al.
Pubblicazione: (2025)

Ensemble-Based Uncertainty Estimation for Code Correctness Estimation
di: Wei, Yunxiang, et al.
Pubblicazione: (2026)

ComplexVCoder: An LLM-Driven Framework for Systematic Generation of Complex Verilog Code
di: Zuo, Jian, et al.
Pubblicazione: (2025)

Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation
di: Jia, Haoxiang, et al.
Pubblicazione: (2025)