CoChat

TIPS: A Prompt Engineering Framework for Code Classification and Generation on Resource-Constrained Systems

Open access
Chen, Wei-Cheng, Chen, Shih-Yeh · 2026 · IEEE Access

The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.

Abstract

Recent advances in AI-assisted programming have demonstrated the potential of Large Language Models (LLMs) in complex code classification and generation. However, their high computational demands and reliance on large-scale datasets limit deployment in resource-constrained environments such as educational tools, edge devices, and small-scale development settings. To address these challenges, this paper introduces the Template-Integrated Prompting System (TIPS), a modular prompt engineering framework designed for lightweight and efficient code analysis. TIPS integrates small-model training, semantically guided demonstration selection, and structured prompt templates to construct an interpretable reasoning pipeline that combines few-shot learning with Chain-of-Thought (CoT) reasoning. Experiments on a benchmark dataset of multithreaded Pthread programs show that TIPS achieves higher precision, recall, and F1-scores than traditional classifiers and prompt-based baselines, even under class imbalance. These results demonstrate that model effectiveness depends not only on scale but also on semantic guidance and structured reasoning. TIPS provides a scalable and interpretable solution, with potential applications in education, software development, and intelligent assistance systems, particularly in resource-constrained environments.

Overview

Integrity signals

Registry

Crossref · 10.1109/access.2026.3658502

Cites

61 of 61 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Research works printed but not linked: 13

  1. Xia, 2022, Practical program repair in the era of large pre-trained language models, arXiv:2210.14179 · arXiv
  2. Chowdhery, 2023, Palm: Scaling language modeling with pathways, J. Mach. Learn. Res., 24, 1
  3. Brown, Language models are few-shot learners, 33, 1877
  4. Grattafiori, 2024, The llama 3 herd of models, arXiv:2407.21783 · arXiv
  5. Chen, 2021, Evaluating large language models trained on code, arXiv:2107.03374 · arXiv
  6. Deanda, 2025, Benchmarking robustness of contrastive learning models for medical image-report retrieval
  7. Li, 2023, Textbooks are all you need II: Phi-1.5 technical report
  8. Javaheripi, 2023, Phi-2: The surprising power of small language models, Microsoft Res. Blog, 1, 3
  9. Taori, 2023, Stanford alpaca: An instruction-following llama model
  10. Touvron, 2023, Llama 2: Open foundation and fine-tuned chat models, arXiv:2307.09288 · arXiv
  11. Oswald, Transformers learn in-context by gradient descent, 35151
  12. Joachims, Transductive inference for text classification using support vector machines, 99, 200
  13. Freund, Experiments with a new boosting algorithm, 96, 148

Cited by

See all 3

Metadata

Authors
Chen, W.-C., & Chen, S.-Y.
Affiliations
  • National Cheng Kung University (TW)
  • Department of Engineering Science, National Cheng Kung University, Tainan, Taiwan
Venue
IEEE Access
Published
2026
Volume
14
Pages
15723-15735
ISSN
2169-3536 (ISSN-L)
OpenAlex
W7125985562
Cited by
3
References
42
Citations by year
2026: 3
FWCI
25.52
Type
journal article
Language
en
Open access
Locations
  • IEEE Access (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Information Systems › Software Engineering Research
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
Keywords
prompt engineering, code classification, code generation, resource-constrained systems, large language models, chain-of-thought reasoning, few-shot learning, demonstration selection, prompt templates, class imbalance, edge devices, AI-assisted programming

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.