Authors : Pawanraj S P; Udayaprasad P K; Amulya P; Sanjana V Hunashikatti

Volume/Issue : Volume 10 - 2025, Issue 7 - July

Google Scholar : https://tinyurl.com/t8nc58xw

Scribd : https://tinyurl.com/4xhuy8e4

DOI : https://doi.org/10.38124/ijisrt/25jul573

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Creating code from human-readable instructions is becoming a major area of research as artificial intelligence is used more and more into software engineering procedures. This paper explores techniques to enhance semantic understanding in AI-based code generation models to improve their ability to interpret human intent and produce accurate, executable code. We investigate the performance of state-of-the-art models such as CodeT5 and PLBART, and propose strategies including prompt engineering, domain-specific fine-tuning and execution-aware evaluation metrics. Our experiments are conducted on datasets like MBPP and APPS, where we evaluate both syntactic correctness and functional accuracy of generated code. Results show that incorporating contextual awareness and structured prompting significantly improves code quality and reduces semantic misinterpretation errors. The findings contribute to the ongoing effort to build more intelligent, reliable and context-aware coding assistants.

Keywords : Code Generation; Natural Language Processing; Program Synthesis; Semantic Understanding; AI For Programming; Transformer Models; Large Language Models (LLMS) ; Prompt Engineering; Fine-Tuning; Execution-Aware Evaluation; Human-AI Collaboration; AI-Assisted Programming; Contextual Code Generation.

References :

1. Chen, M., Shi, Q., Li, H., et al. (2021). Evaluating Large Language Models Trained on Code . arXiv preprint arXiv:2107.03374.
2. Fried, D., Holtzman, A., Raychev, V., et al. (2022). Unified Pretraining for Program Understanding and Generation . arXiv preprint arXiv:2212.10559.
3. Wang, Y., Ruda, M., et al. (2022). MBPP: Mostly Basic Python Problems . Google Research. arXiv preprint arXiv:2209.05659.
4. Guo, D., Duvanenko, N., et al. (2022). CodeXGLUE: A Benchmark Dataset for Code Understanding and Generation . Microsoft Research. arXiv preprint arXiv:2202.12172.
5. J, S, Jumnal, A., P K, U, C, R., Askar, S. S, & Abouhawwash, M. (2024). Bio-Inspired ACO-based Traffic Aware QoS Routing in Software Defined Internet of Things. Applied Artificial Intelligence, 38(1).
6. Aal, S. I. A., Shreyas, J., & Udayaprasad, P. K. (2024). Selecting optimal charcoal company using multi-criteria decision making methodology. Multicriteria algorithms with applications, 3, 15-22.
7. Reddy, C. S., Chouhan, D., Udayaprasad, P. K., Srinidhi, N. N., & Dilipkumar, S. M. (2022). Geographic routing scheme for resource and communication efficiency in the IoT ecosystem using swarm-intelligence based BFO algorithm. Journal of Information Technology Management, 14(1), 41-64.
8. Shreyas, J., Chouhan, D., Rao, S. T., Udayaprasad, P. K., Srinidhi, N. N., & Kumar, S. D. (2021). An energy efficient optimal path selection technique for IoT using genetic algorithm. International Journal of Intelligent Internet of Things Computing, 1(3), 230-248.
9. Austin, J., Odena, A., et al. (2021). Program Synthesis with Large Language Models . arXiv preprint arXiv:2108.07732.
10. Shreyas, J., Chouhan, D., Harshitha, M., Udayaprasad, P. K., & Kumar, S. D. (2022). Network lifetime enhancement routing algorithm for IoT enabled software defined wireless sensor network. In Sustainable advanced computing: select proceedings of ICSAC 2021 (pp. 499-508). Singapore: Springer Singapore.
11. Abdelhafeez, A., Shreyas, J., & Udayaprasad, P. K. (2024). A Fuzzy TOPSIS Method for Assessment Blockchain Technology Strategies. Information Sciences with Applications, 1, 1-9.
12. Shreyas, J., Ajmani, S., Udayaprasad, P. K., Chouhon, D., & SM, D. K. (2021, December). Dynamic routing scheme for linking wireless sensor network towards internet of things. In 2021 5th International Conference on Electrical Information and Communication Technology (EICT) (pp. 1-4). IEEE.
13. Shreyas, J., Shilpa, S., Udayaprasad, P. K., Srinidhi, N. N., & Dilip Kumar, S. M. (2022, November). An Energy Efficient Routing for Emergency Rescue in IoT-Based WSN. In Futuristic Trends in Networks and Computing Technologies: Select Proceedings of Fourth International Conference on FTNCT 2021 (pp. 331-338). Singapore: Springer Nature Singapore.
14. Shreyas, J., Chouhan, D., Rao, S. T., Udayaprasad, P. K., Srinidhi, N. N., & Dilip Kumar, S. M. (2021). EERO: Energy Efficient Route Optimization Technique for IoT Network. In Futuristic Trends in Network and Communication Technologies: Third International Conference, FTNCT 2020, Taganrog, Russia, October 14–16, 2020, Revised Selected Papers, Part II 3 (pp. 207-218). Springer Singapore.
15. Udayaprasad, P. K., Shreyas, J., Srinidhi, N. N., Kumar, S. D., Dayananda, P., Askar, S. S., & Abouhawwash, M. (2024). Energy efficient optimized routing technique with distributed SDN-AI to large scale I-IoT networks. IEEE Access, 12, 2742-2759.