Cover Image

A Causal Perspective on Measuring, Explaining and Mitigating Smells in LLM-Generated Code

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Velasco, Alejandro, Rodriguez-Cardenas, Daniel, Khati, Dipin, Palacio, David N., Alif, Luftar Rahman, Poshyvanyk, Denys
Format:	Preprint
Published:	2025
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study
by: Velasco, Alejandro, et al.
Published: (2024)

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

Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation
by: Khati, Dipin, et al.
Published: (2025)

Towards More Trustworthy and Interpretable LLMs for Code through Syntax-Grounded Explanations
by: Palacio, David N., et al.
Published: (2024)

Tricky$^2$: Towards a Benchmark for Evaluating Human and LLM Error Interactions
by: Granger, Cole, et al.
Published: (2026)

Mapping the Trust Terrain: LLMs in Software Engineering -- Insights and Perspectives
by: Khati, Dipin, et al.
Published: (2025)

Which Syntactic Capabilities Are Statistically Learned by Masked Language Models for Code?
by: Velasco, Alejandro, et al.
Published: (2024)

Measuring Emergent Capabilities of LLMs for Software Engineering: How Far Are We?
by: O'Brien, Conor, et al.
Published: (2024)

SnipGen: A Mining Repository Framework for Evaluating LLMs for Code
by: Rodriguez-Cardenas, Daniel, et al.
Published: (2025)

Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering
by: Rodriguez-Cardenas, Daniel, et al.
Published: (2026)

Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures
by: Rodriguez-Cardenas, Daniel, et al.
Published: (2026)

On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization
by: Crupi, Giuseppe, et al.
Published: (2025)

On Interpreting the Effectiveness of Unsupervised Software Traceability with Information Theory
by: Palacio, David N., et al.
Published: (2024)

Toward a Theory of Causation for Interpreting Neural Code Models
by: Palacio, David N., et al.
Published: (2023)

Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach
by: Yang, Hua, et al.
Published: (2025)

Toward Neurosymbolic Program Comprehension
by: Velasco, Alejandro, et al.
Published: (2025)

Rethinking Software Empirical Studies with Structural Causal Models
by: Rodriguez-Cardenas, Daniel, et al.
Published: (2026)

Testing Practices, Challenges, and Developer Perspectives in Open-Source IoT Platforms
by: Rodriguez-Cardenas, Daniel, et al.
Published: (2025)

A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm
by: Mastropaolo, Antonio, et al.
Published: (2025)

On the Generalizability of Transformer Models to Code Completions of Different Lengths
by: Cooper, Nathan, et al.
Published: (2025)

Towards More Trustworthy Deep Code Models by Enabling Out-of-Distribution Detection
by: Yan, Yanfu, et al.
Published: (2025)

Perspective of Software Engineering Researchers on Machine Learning Practices Regarding Research, Review, and Education
by: Mojica-Hanke, Anamaria, et al.
Published: (2024)

Prompting in Practice: Investigating Software Practitioners' Use of Generative AI Tools
by: Otten, Daniel, et al.
Published: (2025)

How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?
by: Yang, Hua, et al.
Published: (2025)

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

On the Prevalence, Evolution, and Impact of Code Smells in Simulation Modelling Software
by: Mahbub, Riasat, et al.
Published: (2024)

Challenges and Practices in Quantum Software Testing and Debugging: Insights from Practitioners
by: Zappin, Jake, et al.
Published: (2025)

When Quantum Meets Classical: Characterizing Hybrid Quantum-Classical Issues Discussed in Developer Forums
by: Zappin, Jake, et al.
Published: (2024)

Bridging the Quantum Divide: Aligning Academic and Industry Goals in Software Engineering
by: Zappin, Jake, et al.
Published: (2025)

"False negative -- that one is going to kill you": Understanding Industry Perspectives of Static Analysis based Security Testing
by: Ami, Amit Seal, et al.
Published: (2023)

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

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

Developers' Perspectives on Software Licensing: Current Practices, Challenges, and Tools
by: Wintersgill, Nathan, et al.
Published: (2025)

Toward Explaining Large Language Models in Software Engineering Tasks
by: Vitale, Antonio, et al.
Published: (2025)

Developer Perspectives on Licensing and Copyright Issues Arising from Generative AI for Software Development
by: Stalnaker, Trevor, et al.
Published: (2024)

"Don't Be Afraid, Just Learn": Insights from Industry Practitioners to Prepare Software Engineers in the Age of Generative AI
by: Otten, Daniel, et al.
Published: (2026)

Clean Code, Better Models: Enhancing LLM Performance with Smell-Cleaned Dataset
by: Xue, Zhipeng, et al.
Published: (2025)

What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants
by: Hasan, Alif Al, et al.
Published: (2026)

An Event-Driven Tool for Context-Aware Code Smell Detection Using SmellDSL
by: Viegas, Matheus dos Santos, et al.
Published: (2026)

AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development
by: Zhu, Yuecai, et al.
Published: (2026)