Barrier Breakers at BLP-2025 Task 2: Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter

Sajed Jalil, Shuvo Saha, Hossain Mohammad Seym


Abstract
Over the past few years, improving LLM code generation capabilities has been a key focus in NLP research. Despite Bengali having 242 million native speakers worldwide, it receives little attention when it comes to training LLMs. More recently, various fine-tuning and augmented generation techniques have been employed to significantly enhance code generation performance. However, they require considerable expertise and resources to utilize effectively as an end user. The goal of our work is to democratize access to powerful code generation tools in resource-constrained emerging markets, enabling users to leverage them in their native language.We introduce a novel approach that combines Test-Driven Development (TDD) and Code Interpreter (CI), utilizing open-weight models, which improves the baseline accuracy for code generation with Bengali prompts and achieves an overall accuracy of 85%. Our approach requires no finetuning and proves that even the smallest models in the same family can attain up to 98% accuracy compared to the largest models. All of our results are publicly shared in GitHub for validation and reproducibility.
Anthology ID:
2025.banglalp-1.56
Volume:
Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)
Month:
December
Year:
2025
Address:
Mumbai, India
Editors:
Firoj Alam, Sudipta Kar, Shammur Absar Chowdhury, Naeemul Hassan, Enamul Hoque Prince, Mohiuddin Tasnim, Md Rashad Al Hasan Rony, Md Tahmid Rahman Rahman
Venues:
BanglaLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
571–576
Language:
URL:
https://aclanthology.org/2025.banglalp-1.56/
DOI:
Bibkey:
Cite (ACL):
Sajed Jalil, Shuvo Saha, and Hossain Mohammad Seym. 2025. Barrier Breakers at BLP-2025 Task 2: Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter. In Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), pages 571–576, Mumbai, India. Association for Computational Linguistics.
Cite (Informal):
Barrier Breakers at BLP-2025 Task 2: Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter (Jalil et al., BanglaLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.banglalp-1.56.pdf