MétaCan
Menu
← Back to cohort
Record W4415745948 · doi:10.1109/icsme64153.2025.00083

Prompting Matters: Assessing the Effect of Prompting Techniques on LLM-Generated Class Code

2025· article· W4415745948 on OpenAlexaff
John Pangas, Md Mainul Hasan Polash, Ahmad Abdellatif

Bibliographic record

Venuenot available
Typearticle
Language
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsCorrectnessSoftware qualityWorkflowCode reviewCoding (social sciences)Control flowClass (philosophy)Consistency (knowledge bases)Static program analysis

Abstract

fetched live from OpenAlex

The field of software engineering and coding has undergone a significant transformation. The integration of large language models (LLMs), such as ChatGPT, into software development workflows is changing how developers at all skill levels approach coding tasks. Leveraging the capabilities of LLMs, developers can now implement functionalities, fix bugs, and address reviewers' comments more efficiently. However, prior research shows that the effectiveness of LLM-generated code is heavily influenced by the prompting strategy used. Furthermore, generating code at the class level is significantly more complex than at the method level, as it requires maintaining consistency across multiple methods and managing class state. Therefore, this study evaluates the impact of four prompting strategies (i.e., Zero-Shot, Few-Shot, Chain-of-Thought, and Chain-of-Thought-Few-Shot) on GPT and Llama3 in generating class-level code. It assesses the functional correctness and the quality characteristics of the generated code. To better understand how errors differ by prompting strategy, a qualitative analysis of the generated code is conducted for test cases that fail. The findings show that strategies incorporating more contextual guidance (Few-Shot, Chain-of-Thought, and Chain-of-Thought Few-Shot) outperform Zero-Shot prompting by up to 25% in functional correctness, 31% in BLEU-3 score, and 50% in ROUGE-L, while also producing code that is more readable and maintainable. The results also indicate that procedural logic and control flow errors are the most prominent, accounting for 31% of all errors. This study provides valuable insights to guide future research in developing techniques and tools that enhance the quality and reliability of LLM-generated code for complex software development tasks.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.010
metaresearch head score (Gemma)0.146
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.010
Threshold uncertainty score0.051

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.146
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0000.001
Scholarly communication0.0010.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.106
GPT teacher head0.481
Teacher spread0.374 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicArtificial Intelligence in Healthcare and Education→French-language works237,207→