@inproceedings{shahrier-etal-2025-cuet,
title = "{CUET}{\_}{E}xpelliarmus at {BLP}2025 Task 2: Leveraging Instruction Translation and Refinement for {B}angla-to-Python Code Generation with Open-Source {LLM}s",
author = "Shahrier, Md Kaf and
Rashid, Suhana Binta and
Ali Taher, Hasan Mesbaul and
Hoque, Mohammed Moshiul",
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://aclanthology.org/2025.banglalp-1.62/",
pages = "608--614",
ISBN = "979-8-89176-314-2",
abstract = "Large language models (LLMs) have recently shown strong performance in generating code from natural language prompts. However, current benchmarks are primarily focused on English overlooking low-resource languages like Bangla. This creates a critical research gap since there are no well established resources or systematic evaluations for code generation from Bangla instruction. To address the gap, we present a system that generates executable Python code from Bangla instructions. We design a two-stage pipeline where the Bangla instructions are first translated and refined into clear English version to reduce ambiguity and then the python code is generated from the refined instructions with iterative error-correction. For both instruction refinement and code generation we used the open-source GPT-20B OSS model. On the official test set our system achieves competitive results. We also analyze common errors like unclear instruction, logical mistakes, runtime issues and the need for external knowledge beyond the model{'}s training. Overall, our findings show that a simple translation{--}refinement pipeline can be an effective and low-cost approach for code generation in low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shahrier-etal-2025-cuet">
<titleInfo>
<title>CUET_Expelliarmus at BLP2025 Task 2: Leveraging Instruction Translation and Refinement for Bangla-to-Python Code Generation with Open-Source LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Kaf</namePart>
<namePart type="family">Shahrier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suhana</namePart>
<namePart type="given">Binta</namePart>
<namePart type="family">Rashid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="given">Mesbaul</namePart>
<namePart type="family">Ali Taher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naeemul</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enamul</namePart>
<namePart type="given">Hoque</namePart>
<namePart type="family">Prince</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohiuddin</namePart>
<namePart type="family">Tasnim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Rashad</namePart>
<namePart type="given">Al</namePart>
<namePart type="given">Hasan</namePart>
<namePart type="family">Rony</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tahmid</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-314-2</identifier>
</relatedItem>
<abstract>Large language models (LLMs) have recently shown strong performance in generating code from natural language prompts. However, current benchmarks are primarily focused on English overlooking low-resource languages like Bangla. This creates a critical research gap since there are no well established resources or systematic evaluations for code generation from Bangla instruction. To address the gap, we present a system that generates executable Python code from Bangla instructions. We design a two-stage pipeline where the Bangla instructions are first translated and refined into clear English version to reduce ambiguity and then the python code is generated from the refined instructions with iterative error-correction. For both instruction refinement and code generation we used the open-source GPT-20B OSS model. On the official test set our system achieves competitive results. We also analyze common errors like unclear instruction, logical mistakes, runtime issues and the need for external knowledge beyond the model’s training. Overall, our findings show that a simple translation–refinement pipeline can be an effective and low-cost approach for code generation in low-resource languages.</abstract>
<identifier type="citekey">shahrier-etal-2025-cuet</identifier>
<location>
<url>https://aclanthology.org/2025.banglalp-1.62/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>608</start>
<end>614</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUET_Expelliarmus at BLP2025 Task 2: Leveraging Instruction Translation and Refinement for Bangla-to-Python Code Generation with Open-Source LLMs
%A Shahrier, Md Kaf
%A Rashid, Suhana Binta
%A Ali Taher, Hasan Mesbaul
%A Hoque, Mohammed Moshiul
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Hassan, Naeemul
%Y Prince, Enamul Hoque
%Y Tasnim, Mohiuddin
%Y Rony, Md Rashad Al Hasan
%Y Rahman, Md Tahmid Rahman
%S Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-314-2
%F shahrier-etal-2025-cuet
%X Large language models (LLMs) have recently shown strong performance in generating code from natural language prompts. However, current benchmarks are primarily focused on English overlooking low-resource languages like Bangla. This creates a critical research gap since there are no well established resources or systematic evaluations for code generation from Bangla instruction. To address the gap, we present a system that generates executable Python code from Bangla instructions. We design a two-stage pipeline where the Bangla instructions are first translated and refined into clear English version to reduce ambiguity and then the python code is generated from the refined instructions with iterative error-correction. For both instruction refinement and code generation we used the open-source GPT-20B OSS model. On the official test set our system achieves competitive results. We also analyze common errors like unclear instruction, logical mistakes, runtime issues and the need for external knowledge beyond the model’s training. Overall, our findings show that a simple translation–refinement pipeline can be an effective and low-cost approach for code generation in low-resource languages.
%U https://aclanthology.org/2025.banglalp-1.62/
%P 608-614
Markdown (Informal)
[CUET_Expelliarmus at BLP2025 Task 2: Leveraging Instruction Translation and Refinement for Bangla-to-Python Code Generation with Open-Source LLMs](https://aclanthology.org/2025.banglalp-1.62/) (Shahrier et al., BanglaLP 2025)
ACL