Bangla is a low-resource language for code generation, lacking large-scale annotated datasets and tools to transform natural language specifications into executable programs. This makes Bangla-to-code generation a challenging task requiring innovative solutions. To address this, we introduce BanglaForge, a novel framework for generating code from Bangla function descriptions. BanglaForge leverages a retrieval-augmented dual-model collaboration paradigm with self-refinement, combining in-context learning, llm-based translation, systematic prompt engineering, and iterative self-refinement based on execution feedback, where a coder generates initial solutions and a reviewer enhances them for robustness. On the BLP-2025 Bangla Code Generation benchmark, BanglaForge achieves a competitive Pass@1 accuracy of 84.00%, demonstrating the effectiveness of retrieval, model collaboration, and self-refinement for low-resource Bangla code generation.
@article{arxiv.2512.19122,
title = {BanglaForge: LLM Collaboration with Self-Refinement for Bangla Code Generation},
author = {Mahir Labib Dihan and Sadif Ahmed and Md Nafiu Rahman},
journal= {arXiv preprint arXiv:2512.19122},
year = {2025}
}
Comments
Accepted at BLP Workshop @ IJCNLP-AACL 2025. Code is available at https://github.com/mahirlabibdihan/BanglaForge