The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
TIPS: A Prompt Engineering Framework for Code Classification and Generation on Resource-Constrained Systems
Open accessAbstract
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
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 4,688 · cited 1×
“Finally, mixed-quality training data can induce hallucinations in LLMs, leading to unnecessary energy consumption and poor performance in critical tasks [49].”
Large language models for software engineering: survey and open problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE) · doi:10.1109/icse-fose59343.2023.00008 · Cited by 650 · cited 2×
“Moreover, unlike conventional classifiers, the TIPS framework provides not only label predictions but also an interpretable reasoning chain, addressing the lack of transparency in traditional approaches, as noted by Fan et al. [22].”
Large Language Models for Software Engineering: Survey and Open Problems
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023) · arXiv · doi:10.48550/arxiv.2310.03533 · Cited by 523 · cited 2×
“Moreover, unlike conventional classifiers, the TIPS framework provides not only label predictions but also an interpretable reasoning chain, addressing the lack of transparency in traditional approaches, as noted by Fan et al. [22].”
Comparing the quality of human and ChatGPT feedback of students’ writing
Steiss, J., Tate, T., Graham, S., Cruz, J., Hebert, M., Wang, J., Moon, Y., Tseng, W., Warschauer, M., & Olson, C. B. (2024) · Learning and Instruction · doi:10.1016/j.learninstruc.2024.101894 · Cited by 509 · cited 1×
“Beyond programming tasks, LLMs can generate context-aware content to support writing assistance, educational material development, and AI-driven programming education [4].”
A review of green artificial intelligence: Towards a more sustainable future
Bolón-Canedo, V., Morán-Fernández, L., Cancela, B., & Alonso-Betanzos, A. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128096 · Cited by 486 · cited 1×
“In compute-constrained scenarios such as IoT, edge computing, and cloud devices, memory efficiency and execution latency are of paramount importance [40], [41].”
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Ainslie, J., Lee-Thorp, J., de Jong, M., Zemlyanskiy, Y., Lebron, F., & Sanghai, S. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.298 · Cited by 454
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Ainslie, J., Lee-Thorp, J., de Jong, M., Zemlyanskiy, Y., Lebrón, F., & Sanghai, S. (2023) · arXiv · doi:10.48550/arxiv.2305.13245 · Cited by 447 · cited 1×
“Jiang et al. [15] introduced Mistral, an efficient 7B model incorporating Grouped Query Attention (GQA) [60] for faster inference and Sliding Window Attention (SWA) [61] to effectively handle long sequences.”
Efficient and precise datarace detection for multithreaded object-oriented programs
Choi, J.-D., Lee, K., Loginov, A., O'Callahan, R., Sarkar, V., & Sridharan, M. (2002) · Proceedings of the ACM SIGPLAN 2002 conference on Programming language design and implementation · doi:10.1145/512529.512560 · Cited by 441 · cited 1×
“Choi et al. [29] proposed a hybrid framework combining static and dynamic analysis to improve the detection of race conditions in object-oriented programs.”
Unveiling security, privacy, and ethical concerns of ChatGPT
Wu, X., Duan, R., & Ni, J. (2024) · Journal of Information and Intelligence · doi:10.1016/j.jiixd.2023.10.007 · Cited by 314
Research works printed but not linked: 29
- Xia, 2022, Practical program repair in the era of large pre-trained language models, arXiv:2210.14179 · arXiv
- Chowdhery, 2023, Palm: Scaling language modeling with pathways, J. Mach. Learn. Res., 24, 1
- Brown, Language models are few-shot learners, 33, 1877
- Jiang, 2024, Mixtral of experts, arXiv:2401.04088 · arXiv
- Grattafiori, 2024, The llama 3 herd of models, arXiv:2407.21783 · arXiv
- Frantar, 2022, GPTQ: Accurate post-training quantization for generative pre-trained transformers, arXiv:2210.17323 · arXiv
- Chen, 2021, Evaluating large language models trained on code, arXiv:2107.03374 · arXiv
- Yang, 2024, Chain-of-thought in large language models: Decoding, projection, and activation, arXiv:2412.03944 · arXiv
- Malakar, 2024, RaceFixer—An automated data race fixer, arXiv:2401.04221 · arXiv
- Deanda, 2025, Benchmarking robustness of contrastive learning models for medical image-report retrieval
- Qiu, 2024, How efficient is LLM-generated code? A rigorous & high-standard benchmark, arXiv:2406.06647 · arXiv
- Fried, 2022, InCoder: A generative model for code infilling and synthesis, arXiv:2204.05999 · arXiv
- Li, 2023, StarCoder: May the source be with you!, arXiv:2305.06161 · arXiv
- Rozière, 2023, Code llama: Open foundation models for code, arXiv:2308.12950 · arXiv
- Yu, 2024, HumanEval pro and MBPP pro: Evaluating large language models on self-invoking code generation, arXiv:2412.21199 · arXiv
- Gunasekar, 2023, Textbooks are all you need, arXiv:2306.11644 · arXiv
- Li, 2023, Textbooks are all you need II: Phi-1.5 technical report
- Javaheripi, 2023, Phi-2: The surprising power of small language models, Microsoft Res. Blog, 1, 3
- Taori, 2023, Stanford alpaca: An instruction-following llama model
- Beltagy, 2020, Longformer: The long-document transformer, arXiv:2004.05150 · arXiv
- Touvron, 2023, Llama 2: Open foundation and fine-tuned chat models, arXiv:2307.09288 · arXiv
- Tunstall, 2023, Zephyr: Direct distillation of LM alignment, arXiv:2310.16944 · arXiv
- Hu, 2024, MiniCPM: Unveiling the potential of small language models with scalable training strategies, arXiv:2404.06395 · arXiv
- Hiraou, 2024, Context-masked meta-prompting for privacy-preserving LLM adaptation in finance, arXiv:2407.18920 · arXiv
- Zhao, 2023, Enhancing zero-shot chain-of-thought reasoning in large language models through logic, arXiv:2309.13339 · arXiv
- Wang, 2022, Self-consistency improves chain of thought reasoning in language models, arXiv:2203.11171 · arXiv
- Oswald, Transformers learn in-context by gradient descent, 35151
- Joachims, Transductive inference for text classification using support vector machines, 99, 200
- Freund, Experiments with a new boosting algorithm, 96, 148
Cited by
Exploring the Capabilities of an LLM from CFD Simulations of Turbulent Flow in a Manifold
Morano-Okuno, H. R., Vicente-Cisneros, A. R. S., & Sandoval-Benitez, G. (2026) · Applied Sciences · doi:10.3390/app16115300
Inteligencia artificial en la ingenieria de software
Salazar, S. (2026) · SAP Engineering and Industry · doi:10.62486/ei2026103
Structure-Aware Thesis Content Description Using Large Language Models
Hrvacević, L., Dodović, M., Tufegdžić, J., & Mišić, M. J. (2026) · International Conference on Electrical, Electronic and Computing Engineering (IcETRAN) · doi:10.1109/icetran71739.2026.11727876
“In addition, the TIPS [19] metric is employed as a composite measure that combines semantic, lexical, and syntactic similarity into a single score, providing a more comprehensive evaluation of generated text.”
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
- gold
- doi.org
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: TIPS: A Prompt Engineering Framework for Code Classification and Generation on Resource-Constrained Systems. https://app.cochat.ai/papers/10.1109/access.2026.3658502
- The paper
- Chen, W.-C., & Chen, S.-Y. (2026). TIPS: A Prompt Engineering Framework for Code Classification and Generation on Resource-Constrained Systems. IEEE Access. https://doi.org/10.1109/access.2026.3658502
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.