Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	AKLI, Amal, PAPADAKIS, Mike, CORDY, Maxime, TRAON, Yves Le
Format:	Preprint
Published:	2026
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis
by: Akli, Amal, et al.
Published: (2026)

When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions
by: Larbi, Maya, et al.
Published: (2025)

One Model, Many Skills: Parameter-Efficient Fine-Tuning for Multitask Code Analysis
by: Akli, Amal, et al.
Published: (2026)

An Exploratory Study of Bayesian Prompt Optimization for Test-Driven Code Generation with Large Language Models
by: Tomar, Shlok, et al.
Published: (2025)

Inferring Code Correctness from Specification
by: Florian, Tambon, et al.
Published: (2026)

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

An Empirical Study on the Effects of System Prompts in Instruction-Tuned Models for Code Generation
by: Cheng, Zaiyu, et al.
Published: (2026)

iCodeReviewer: Improving Secure Code Review with Mixture of Prompts
by: Peng, Yun, et al.
Published: (2025)

Prompt Alchemy: Automatic Prompt Refinement for Enhancing Code Generation
by: Ye, Sixiang, et al.
Published: (2025)

Code Roulette: How Prompt Variability Affects LLM Code Generation
by: Paleyes, Andrei, et al.
Published: (2025)

The Readability Spectrum: Patterns, Issues, and Prompt Effects in LLM-Generated Code
by: Ye, Hengzhi, et al.
Published: (2026)

GenCode: A Generic Data Augmentation Framework for Boosting Deep Learning-Based Code Understanding
by: Dong, Zeming, et al.
Published: (2024)

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

Evaluating Large Language Models for Code Translation: Effects of Prompt Language and Prompt Design
by: Aljagthami, Aamer, et al.
Published: (2025)

Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts
by: Ouyang, Sheng, et al.
Published: (2025)

Modularization is Better: Effective Code Generation with Modular Prompting
by: Pan, Ruwei, et al.
Published: (2025)

CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs
by: He, Pengfei, et al.
Published: (2025)

Toward Green Code: Prompting Small Language Models for Energy-Efficient Code Generation
by: Ashraf, Humza, et al.
Published: (2025)

Tuning LLM-based Code Optimization via Meta-Prompting: An Industrial Perspective
by: Gong, Jingzhi, et al.
Published: (2025)

Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation
by: Janzen, Lynn, et al.
Published: (2026)

The Impact of Generative AI on Code Expertise Models: An Exploratory Study
by: Cury, Otávio, et al.
Published: (2025)

Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study
by: Dong, Zeming, et al.
Published: (2023)

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

Guidelines to Prompt Large Language Models for Code Generation: An Empirical Characterization
by: Midolo, Alessandro, et al.
Published: (2026)

Prompt-based Code Completion via Multi-Retrieval Augmented Generation
by: Tan, Hanzhuo, et al.
Published: (2024)

Evaluating the Environmental Impact of using SLMs and Prompt Engineering for Code Generation
by: Mamun, Md Afif Al, et al.
Published: (2026)

Selection of Prompt Engineering Techniques for Code Generation through Predicting Code Complexity
by: Wang, Chung-Yu, et al.
Published: (2024)

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

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

Configuring Agentic AI Coding Tools: An Exploratory Study
by: Galster, Matthias, et al.
Published: (2026)

LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT
by: Xu, Zhenyu, et al.
Published: (2024)

Automated Prompt Generation for Code Intelligence: An Empirical study and Experience in WeChat
by: Ji, Kexing, et al.
Published: (2025)

On Fixing Insecure AI-Generated Code through Model Fine-Tuning and Prompting Strategies
by: Jahromi, Ali Soltanian Fard, et al.
Published: (2026)

Zero-Shot Code Representation Learning via Prompt Tuning
by: Cui, Nan, et al.
Published: (2024)

Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code
by: Shin, Jiho, et al.
Published: (2023)

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

Software Fairness: An Analysis and Survey
by: Soremekun, Ezekiel, et al.
Published: (2022)

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

LLM Assisted Coding with Metamorphic Specification Mutation Agent
by: Akhond, Mostafijur Rahman, et al.
Published: (2025)

When Retriever Meets Generator: A Joint Model for Code Comment Generation
by: Le, Tien P. T., et al.
Published: (2025)