Image de couverture de livre

When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	AKLI, Amal, PAPADAKIS, Mike, CORDY, Maxime, TRAON, Yves Le
Format:	Preprint
Publié:	2026
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
par: Akli, Amal, et autres
Publié: (2026)

When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions
par: Larbi, Maya, et autres
Publié: (2025)

One Model, Many Skills: Parameter-Efficient Fine-Tuning for Multitask Code Analysis
par: Akli, Amal, et autres
Publié: (2026)

An Exploratory Study of Bayesian Prompt Optimization for Test-Driven Code Generation with Large Language Models
par: Tomar, Shlok, et autres
Publié: (2025)

Inferring Code Correctness from Specification
par: Florian, Tambon, et autres
Publié: (2026)

Prompt Optimization for LLM Code Generation via Reinforcement Learning
par: Esfahani, Ali Mohammadi, et autres
Publié: (2026)

An Empirical Study on the Effects of System Prompts in Instruction-Tuned Models for Code Generation
par: Cheng, Zaiyu, et autres
Publié: (2026)

iCodeReviewer: Improving Secure Code Review with Mixture of Prompts
par: Peng, Yun, et autres
Publié: (2025)

Prompt Alchemy: Automatic Prompt Refinement for Enhancing Code Generation
par: Ye, Sixiang, et autres
Publié: (2025)

Code Roulette: How Prompt Variability Affects LLM Code Generation
par: Paleyes, Andrei, et autres
Publié: (2025)

The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code
par: Ye, Hengzhi, et autres
Publié: (2026)

GenCode: A Generic Data Augmentation Framework for Boosting Deep Learning-Based Code Understanding
par: Dong, Zeming, et autres
Publié: (2024)

Structured Safety Auditing for Balancing Code Correctness and Content Safety in LLM-Generated Code
par: Tan, Honghao, et autres
Publié: (2026)

Evaluating Large Language Models for Code Translation: Effects of Prompt Language and Prompt Design
par: Aljagthami, Aamer, et autres
Publié: (2025)

Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts
par: Ouyang, Sheng, et autres
Publié: (2025)

Modularization is Better: Effective Code Generation with Modular Prompting
par: Pan, Ruwei, et autres
Publié: (2025)

CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs
par: He, Pengfei, et autres
Publié: (2025)

Toward Green Code: Prompting Small Language Models for Energy-Efficient Code Generation
par: Ashraf, Humza, et autres
Publié: (2025)

Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective
par: Gong, Jingzhi, et autres
Publié: (2025)

Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation
par: Janzen, Lynn, et autres
Publié: (2026)

The Impact of Generative AI on Code Expertise Models: An Exploratory Study
par: Cury, Otávio, et autres
Publié: (2025)

Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study
par: Dong, Zeming, et autres
Publié: (2023)

Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation
par: Cui, Yi
Publié: (2025)

Guidelines to Prompt Large Language Models for Code Generation: An Empirical Characterization
par: Midolo, Alessandro, et autres
Publié: (2026)

Prompt-based Code Completion via Multi-Retrieval Augmented Generation
par: Tan, Hanzhuo, et autres
Publié: (2024)

Evaluating the Environmental Impact of using SLMs and Prompt Engineering for Code Generation
par: Mamun, Md Afif Al, et autres
Publié: (2026)

Selection of Prompt Engineering Techniques for Code Generation through Predicting Code Complexity
par: Wang, Chung-Yu, et autres
Publié: (2024)

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
par: Tessa, Melissa, et autres
Publié: (2026)

Show and Tell: Prompt Strategies for Style Control in Multi-Turn LLM Code Generation
par: Bohr, Jeremiah
Publié: (2025)

Configuring Agentic AI Coding Tools: An Exploratory Study
par: Galster, Matthias, et autres
Publié: (2026)

LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT
par: Xu, Zhenyu, et autres
Publié: (2024)

Automated Prompt Generation for Code Intelligence: An Empirical study and Experience in WeChat
par: Ji, Kexing, et autres
Publié: (2025)

On Fixing Insecure AI-Generated Code through Model Fine-Tuning and Prompting Strategies
par: Jahromi, Ali Soltanian Fard, et autres
Publié: (2026)

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

Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code
par: Shin, Jiho, et autres
Publié: (2023)

DSL or Code? Evaluating the Quality of LLM-Generated Algebraic Specifications: A Case Study in Optimization at Kinaxis
par: Ayoughi, Negin, et autres
Publié: (2026)

Software Fairness: An Analysis and Survey
par: Soremekun, Ezekiel, et autres
Publié: (2022)

Assessing Correctness in LLM-Based Code Generation via Uncertainty Estimation
par: Sharma, Arindam, et autres
Publié: (2025)

LLM Assisted Coding with Metamorphic Specification Mutation Agent
par: Akhond, Mostafijur Rahman, et autres
Publié: (2025)

When Retriever Meets Generator: A Joint Model for Code Comment Generation
par: Le, Tien P. T., et autres
Publié: (2025)