CoChat

The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.

Enhancing Code Generation Using Instruction-Tuned Transformer Models for Multi-Language Software Development

Sathiyavathi, A., Gowri, C. Gethara, Sundar, R., Theo, J. Arockia, Poornimadevi, L., S, Suberiya Begum · 2026 · 2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN)

Abstract

The rapid growth of multi-language software development has increased the demand for intelligent systems capable of generating accurate and reliable source code from natural language instructions. Transformer-based models have shown significant potential in automated code generation; however, their effectiveness is often limited by inadequate alignment with user intent and challenges in cross-language generalization. This research investigates the enhancement of code generation using instruction-tuned transformer models to improve adaptability across multiple programming languages. A structured experimental methodology is adopted, incorporating a pretrained transformer baseline, instruction tuning, and systematic evaluation supported by a built-in benchmark dataset. Exploratory data analysis and visualization techniques are employed to understand data characteristics and support reliable interpretation of results. The findings demonstrate that instruction tuning improves instruction adherence, code consistency, and generalization capability in multi-language scenarios. The proposed framework provides a reproducible and scalable foundation for advancing automated code generation systems in modern software development environments.

Overview

Integrity signals

Registry

Crossref · 10.1109/qpain69676.2026.11546564

Cites

56 of 56 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 56 references

Research works printed but not linked: 6

  1. Stone, 2026, Responsible AI in teaching and learning
  2. Rizki, 2024, Digital leadership (theory and implementation in higher education), J. Ekon., 13, 389
  3. Paris, 2025, Artificial intelligence and academic professions, SSRN Electron. J.
  4. He, 2025, Thriving in the age of AI: Navigating AI identity threat through AI job crafting
  5. 2025, Survey: Higher ed faculty mixed on EdTech and AI, CIN Faculty EdTech Survey
  6. G, 2025, Automatic analysis of happy/sad face image with deep learning model, 1

Cited by

Still being checked.

Metadata

Authors
Sathiyavathi, A., Gowri, C. G., Sundar, R., Theo, J. A., Poornimadevi, L., & S, S. B.
Affiliations
  • Vel Tech Ranga Sanku Arts College,Department of English,Chennai,India,600055
  • Rajalakshmi Institute of Technology,Department of Computer Science and Engineering,Chennai,India,600124
  • AMET University (IN)
  • Saveetha University (IN)
  • S N S College of Technology,Department of Computer Science and Engineering,Coimbatore,India,641035
  • B.S. Abdur Rahman Crescent Institute of Science & Technology (IN)
Venue
2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN)
Publisher
IEEE
Published
2026-04-16
Pages
1-6
OpenAlex
W7164421847
Cited by
0
References
56
FWCI
0.00
Type
conference paper
Language
en
Open access
closed
Locations
IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Information Systems › Software Engineering Research
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
Keywords
automatic code generation, instruction tuning, transformer models, cross-lingual generalization, natural language to code, programming languages

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: Enhancing Code Generation Using Instruction-Tuned Transformer Models for Multi-Language Software Development. https://app.cochat.ai/papers/10.1109/qpain69676.2026.11546564
The paper
Sathiyavathi, A., Gowri, C. G., Sundar, R., Theo, J. A., Poornimadevi, L., & S, S. B. (2026). Enhancing Code Generation Using Instruction-Tuned Transformer Models for Multi-Language Software Development. 2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN). https://doi.org/10.1109/qpain69676.2026.11546564

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.