@inproceedings{rahman-etal-2025-alphaborno,
title = "{A}lpha{B}orno at {BLP}-2025 Task 2: Code Generation with Structured Prompts and Execution Feedback",
author = "Rahman, Mohammad Ashfaq Ur and
Shochcho, Muhtasim Ibteda and
Fahim, Md",
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-1.63/",
pages = "615--623",
ISBN = "979-8-89176-314-2",
abstract = "This paper explores various prompting strategies in the BLP-2025 Shared Task 2, utilizing a pipeline that first translates Bangla problem descriptions into English with GPT-4o,then applies techniques like zero-shot, few-shot,chain of thought, synthetic test case integration, and a self-repair loop. We evaluated fourLLMs (GPT-4o, Grok-3, Claude 3.7 Sonnet,and Qwen2.5-Coder 14B). Our findings revealthat while traditional methods like few-shotand chain-of-thought prompting provided inconsistent gains, the integration of explicit unittests delivered a substantial performance boostacross all models. The most effective strategycombined zero-shot prompting with these synthetic tests and a self-repair loop, leading GPT4o to achieve a top Pass@1 score of 72.2{\%}.These results represent the value of using explicit constraints and iterative feedback in codegeneration, offering a solid framework that improves the model{'}s code generation capabilities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahman-etal-2025-alphaborno">
<titleInfo>
<title>AlphaBorno at BLP-2025 Task 2: Code Generation with Structured Prompts and Execution Feedback</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Ashfaq</namePart>
<namePart type="given">Ur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhtasim</namePart>
<namePart type="given">Ibteda</namePart>
<namePart type="family">Shochcho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="family">Fahim</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>This paper explores various prompting strategies in the BLP-2025 Shared Task 2, utilizing a pipeline that first translates Bangla problem descriptions into English with GPT-4o,then applies techniques like zero-shot, few-shot,chain of thought, synthetic test case integration, and a self-repair loop. We evaluated fourLLMs (GPT-4o, Grok-3, Claude 3.7 Sonnet,and Qwen2.5-Coder 14B). Our findings revealthat while traditional methods like few-shotand chain-of-thought prompting provided inconsistent gains, the integration of explicit unittests delivered a substantial performance boostacross all models. The most effective strategycombined zero-shot prompting with these synthetic tests and a self-repair loop, leading GPT4o to achieve a top Pass@1 score of 72.2%.These results represent the value of using explicit constraints and iterative feedback in codegeneration, offering a solid framework that improves the model’s code generation capabilities.</abstract>
<identifier type="citekey">rahman-etal-2025-alphaborno</identifier>
<location>
<url>https://aclanthology.org/2025.banglalp-1.63/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>615</start>
<end>623</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AlphaBorno at BLP-2025 Task 2: Code Generation with Structured Prompts and Execution Feedback
%A Rahman, Mohammad Ashfaq Ur
%A Shochcho, Muhtasim Ibteda
%A Fahim, Md
%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 rahman-etal-2025-alphaborno
%X This paper explores various prompting strategies in the BLP-2025 Shared Task 2, utilizing a pipeline that first translates Bangla problem descriptions into English with GPT-4o,then applies techniques like zero-shot, few-shot,chain of thought, synthetic test case integration, and a self-repair loop. We evaluated fourLLMs (GPT-4o, Grok-3, Claude 3.7 Sonnet,and Qwen2.5-Coder 14B). Our findings revealthat while traditional methods like few-shotand chain-of-thought prompting provided inconsistent gains, the integration of explicit unittests delivered a substantial performance boostacross all models. The most effective strategycombined zero-shot prompting with these synthetic tests and a self-repair loop, leading GPT4o to achieve a top Pass@1 score of 72.2%.These results represent the value of using explicit constraints and iterative feedback in codegeneration, offering a solid framework that improves the model’s code generation capabilities.
%U https://aclanthology.org/2025.banglalp-1.63/
%P 615-623
Markdown (Informal)
[AlphaBorno at BLP-2025 Task 2: Code Generation with Structured Prompts and Execution Feedback](https://aclanthology.org/2025.banglalp-1.63/) (Rahman et al., BanglaLP 2025)
ACL