@inproceedings{roy-2025-codeanubad,
    title = "{C}ode{A}nubad at {BLP}-2025 Task 2: Efficient {B}angla-to-Python Code Generation via Iterative {L}o{RA} Fine-Tuning of Gemma-2",
    author = "Roy, Soumyajit",
    editor = "Alam, Firoj  and
      Kar, Sudipta  and
      Chowdhury, Shammur Absar  and
      Hassan, Naeemul  and
      Prince, Enamul Hoque  and
      Tasnim, Mohiuddin  and
      Rony, Md Rashad Al Hasan  and
      Rahman, Md Tahmid Rahman",
    booktitle = "Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.banglalp-1.53/",
    pages = "556--560",
    ISBN = "979-8-89176-314-2",
    abstract = "This paper presents our submission for Task 2 of the Bangla Language Processing (BLP) Workshop, which focuses on generating Python code from Bangla programming prompts in a low-resource setting. We address this challenge by fine-tuning the gemma-2-9b instruction-tuned model using parameter-efficient fine-tuning (PEFT) with QLoRA. We propose an iterative self-improvement strategy that augments the extremely limited training data (74 examples) by reusing verified correct predictions from the development set, alongside LoRA rank experiments (8, 16, 32), observing a clear correlation between rank and accuracy, with rank 32 delivering the best results. Compared to translation-based and retrieval-augmented baselines, our approach achieves significantly higher accuracy, with a pass rate of 47{\%} on the development set and 37{\%} on the hidden test set. These results highlight the effectiveness of combining iterative data augmentation with rank optimisation for specialised, low-resource code generation tasks."
}