Imagen de Portada

Programming Language Confusion: When Code LLMs Can't Keep their Languages Straight

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Moumoula, Micheline Bénédicte, Nikiema, Serge Lionel, Kabore, Abdoul Kader, Klein, Jacques, Bissyande, Tegawendé F.
Formato:	Preprint
Publicado:	2025
Materias:	Software Engineering
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation
por: Moumoula, Micheline Bénédicte, et al.
Publicado: (2025)

The Struggles of LLMs in Cross-lingual Code Clone Detection
por: Moumoula, Micheline Bénédicte, et al.
Publicado: (2024)

The Code Barrier: What LLMs Actually Understand?
por: Nikiema, Serge Lionel, et al.
Publicado: (2025)

Learned or Memorized ? Quantifying Memorization Advantage in Code LLMs
por: Euraste, Djiré Albérick, et al.
Publicado: (2026)

Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study
por: Nikiema, Serge Lionel, et al.
Publicado: (2025)

Correctness isnt Efficiency: Runtime Memory Divergence in LLM-Generated Code
por: Rajput, Prateek, et al.
Publicado: (2026)

How Small Transformation Expose the Weakness of Semantic Similarity Measures
por: Nikiema, Serge Lionel, et al.
Publicado: (2025)

Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning
por: Tang, Xunzhu, et al.
Publicado: (2025)

Characterizing Build Compromises Through Vulnerability Disclosure Analysis
por: Diao, Maimouna Tamah, et al.
Publicado: (2025)

Dynamic Stability of LLM-Generated Code
por: Rajput, Prateek, et al.
Publicado: (2025)

From Rookie to Expert: Manipulating LLMs for Automated Vulnerability Exploitation in Enterprise Software
por: Diouf, Moustapha Awwalou, et al.
Publicado: (2025)

Security Evaluation of Android apps in budget African Mobile Devices
por: Diallo, Alioune, et al.
Publicado: (2025)

Large-scale, Independent and Comprehensive study of the power of LLMs for test case generation
por: Ouédraogo, Wendkûuni C., et al.
Publicado: (2024)

Enriching Automatic Test Case Generation by Extracting Relevant Test Inputs from Bug Reports
por: Ouédraogo, Wendkûuni C., et al.
Publicado: (2023)

Security smells in infrastructure as code: a taxonomy update beyond the seven sins
por: War, Aicha, et al.
Publicado: (2025)

AndroLibZoo: A Reliable Dataset of Libraries Based on Software Dependency Analysis
por: Samhi, Jordan, et al.
Publicado: (2023)

Detection of security smells in IaC scripts through semantics-aware code and language processing
por: War, Aicha, et al.
Publicado: (2025)

Evaluating Large Language Models in detecting Secrets in Android Apps
por: Alecci, Marco, et al.
Publicado: (2025)

Human-Aligned Code Readability Assessment with Large Language Models
por: Ouédraogo, Wendkûuni C., et al.
Publicado: (2025)

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning
por: Yang, Boyang, et al.
Publicado: (2024)

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

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
por: Tessa, Melissa, et al.
Publicado: (2026)

Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance
por: Song, Yewei, et al.
Publicado: (2024)

Measuring LLM Code Generation Stability via Structural Entropy
por: Song, Yewei, et al.
Publicado: (2025)

Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement
por: Luo, Wenqiang, et al.
Publicado: (2025)

Software Security in Software-Defined Networking: A Systematic Literature Review
por: Diouf, Moustapha Awwalou, et al.
Publicado: (2025)

Call Graph Soundness in Android Static Analysis
por: Samhi, Jordan, et al.
Publicado: (2024)

CodeAgent: Autonomous Communicative Agents for Code Review
por: Tang, Xunzhu, et al.
Publicado: (2024)

CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors
por: Yang, Boyang, et al.
Publicado: (2024)

SIEVE: Towards Verifiable Certification for Code-datasets
por: Mbodji, Fatou Ndiaye, et al.
Publicado: (2025)

Patch-CLIP: A Patch-Text Pre-Trained Model
por: Tang, Xunzhu, et al.
Publicado: (2023)

When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair
por: Luo, Wenqiang, et al.
Publicado: (2024)

MalLoc: Toward Fine-grained Android Malicious Payload Localization via LLMs
por: Sun, Tiezhu, et al.
Publicado: (2025)

ContractTrace: Retracing Smart Contract Versions for Security Analyses
por: Mbodji, Fatou Ndiaye, et al.
Publicado: (2024)

In-Context Code-Text Learning for Bimodal Software Engineering
por: Tang, Xunzhu, et al.
Publicado: (2024)

Perplexed: Understanding When Large Language Models are Confused
por: Cooper, Nathan, et al.
Publicado: (2024)

Beyond Surface Similarity: Evaluating LLM-Based Test Refactorings with Structural and Semantic Awareness
por: Ouédraogo, Wendkûuni C., et al.
Publicado: (2025)

Enhancing Text-to-SQL Translation for Financial System Design
por: Song, Yewei, et al.
Publicado: (2023)

Test smells in LLM-Generated Unit Tests
por: Ouédraogo, Wendkûuni C., et al.
Publicado: (2024)

Rethinking Cognitive Complexity for Unit Tests: Toward a Readability-Aware Metric Grounded in Developer Perception
por: Ouédraogo, Wendkûuni C., et al.
Publicado: (2025)