Image de couverture de livre

Neuron-Guided Interpretation of Code LLMs: Where, Why, and How?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yin, Zhe, Gu, Xiaodong, Shen, Beijun
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

Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs
par: Xie, Chen, et autres
Publié: (2025)

Just-In-Time Software Defect Prediction via Bi-modal Change Representation Learning
par: Jiang, Yuze, et autres
Publié: (2024)

In Line with Context: Repository-Level Code Generation via Context Inlining
par: Hu, Chao, et autres
Publié: (2026)

CatchAll: Repository-Aware Exception Handling with Knowledge-Guided LLMs
par: Tao, Qingxiao, et autres
Publié: (2026)

APIRAT: Integrating Multi-source API Knowledge for Enhanced Code Translation with LLMs
par: Wang, Chaofan, et autres
Publié: (2025)

Unraveling the Potential of Large Language Models in Code Translation: How Far Are We?
par: Tao, Qingxiao, et autres
Publié: (2024)

Zero-Shot Code Representation Learning via Prompt Tuning
par: Cui, Nan, et autres
Publié: (2024)

EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation
par: Wang, Chaofan, et autres
Publié: (2025)

Cross-Domain Deep Code Search with Meta Learning
par: Chai, Yitian, et autres
Publié: (2022)

Rethinking Code Complexity Through the Lens of Large Language Models
par: Xie, Chen, et autres
Publié: (2026)

Beyond Language Boundaries: Uncovering Programming Language Families for Code Language Models
par: Yun, Shangbo, et autres
Publié: (2025)

LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues
par: Lin, Yalan, et autres
Publié: (2024)

When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning
par: Morabito, Roberto, et autres
Publié: (2025)

LongCodeZip: Compress Long Context for Code Language Models
par: Shi, Yuling, et autres
Publié: (2025)

Rectifier: Code Translation with Corrector via LLMs
par: Yin, Xin, et autres
Publié: (2024)

Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs
par: Chen, Yujia, et autres
Publié: (2026)

Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
par: Pan, Zhenyu, et autres
Publié: (2024)

RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
par: Mo, Wenjie Jacky, et autres
Publié: (2025)

Protocode: Prototype-Driven Interpretability for Code Generation in LLMs
par: Bodla, Krishna Vamshi, et autres
Publié: (2025)

Coherence Collapse: Diagnosing Why Code Agents Fail After Reaching the Right Code
par: Kim, Myeongsoo, et autres
Publié: (2026)

Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization
par: Wu, Yuhan, et autres
Publié: (2026)

Generating Energy-Efficient Code via Large-Language Models -- Where are we now?
par: Apsan, Radu, et autres
Publié: (2025)

LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations
par: Han, Junxiao, et autres
Publié: (2025)

Search-Based LLMs for Code Optimization
par: Gao, Shuzheng, et autres
Publié: (2024)

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers
par: Shi, Yuling, et autres
Publié: (2024)

$\mathbb{USCD}$: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding
par: Wang, Shuai, et autres
Publié: (2024)

Migrating Code At Scale With LLMs At Google
par: Ziftci, Celal, et autres
Publié: (2025)

Analysis on LLMs Performance for Code Summarization
par: Akib, Md. Ahnaf, et autres
Publié: (2024)

Where Code Meets Natural Language: Taxonomy-Driven Information Flow Analysis for LLM-Integrated Applications
par: Xu, Zihao, et autres
Publié: (2026)

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

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis
par: Yang, Weiqing, et autres
Publié: (2024)

Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations
par: Palacio, David N., et autres
Publié: (2024)

How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?
par: Yang, Hua, et autres
Publié: (2025)

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
par: Ehsani, Ramtin, et autres
Publié: (2026)

The Code Barrier: What LLMs Actually Understand?
par: Nikiema, Serge Lionel, et autres
Publié: (2025)

Do Code LLMs Understand Design Patterns?
par: Pan, Zhenyu, et autres
Publié: (2025)

Function-to-Style Guidance of LLMs for Code Translation
par: Zhang, Longhui, et autres
Publié: (2025)

Evaluating the Energy-Efficiency of the Code Generated by LLMs
par: Islam, Md Arman, et autres
Publié: (2025)

CodeTF: One-stop Transformer Library for State-of-the-art Code LLMs
par: Bui, Nghi D. Q., et autres
Publié: (2023)

Mastering the Craft of Data Synthesis for CodeLLMs
par: Chen, Meng, et autres
Publié: (2024)