@inproceedings{farazi-reza-2025-troopers,
title = "Troopers at {BLP}-2025 Task 2: Reward-Selective Fine-Tuning based Code Generation Approach for {B}angla Prompts",
author = "Farazi, Musa Tur and
Reza, Nufayer Jahan",
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-1.54/",
pages = "561--565",
ISBN = "979-8-89176-314-2",
abstract = "We present a formally grounded description of a reward-selective fine-tuning (RSFT) pipeline for code generation from Bangla natural-language prompts. The implemented system mines candidate programs via temperature and nucleus sampling, executes candidates in a sandbox and retains programs that pass all unit tests, performs supervised fine-tuning (SFT) on winners using parameter-efficient Low rank adaptation (LoRA) adapters, and augments robustness through fuzzed asserts. We specify the exact objectives and estimators used, provide a Bangla-aware preprocessing recipe, prove simple properties of the sampling budget, and report an ablation showing the effect of inference sample budget $K$ on accuracy. We also include a threat model for safe execution. Our codes are available on GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="farazi-reza-2025-troopers">
<titleInfo>
<title>Troopers at BLP-2025 Task 2: Reward-Selective Fine-Tuning based Code Generation Approach for Bangla Prompts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Musa</namePart>
<namePart type="given">Tur</namePart>
<namePart type="family">Farazi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nufayer</namePart>
<namePart type="given">Jahan</namePart>
<namePart type="family">Reza</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>We present a formally grounded description of a reward-selective fine-tuning (RSFT) pipeline for code generation from Bangla natural-language prompts. The implemented system mines candidate programs via temperature and nucleus sampling, executes candidates in a sandbox and retains programs that pass all unit tests, performs supervised fine-tuning (SFT) on winners using parameter-efficient Low rank adaptation (LoRA) adapters, and augments robustness through fuzzed asserts. We specify the exact objectives and estimators used, provide a Bangla-aware preprocessing recipe, prove simple properties of the sampling budget, and report an ablation showing the effect of inference sample budget K on accuracy. We also include a threat model for safe execution. Our codes are available on GitHub.</abstract>
<identifier type="citekey">farazi-reza-2025-troopers</identifier>
<location>
<url>https://aclanthology.org/2025.banglalp-1.54/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>561</start>
<end>565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Troopers at BLP-2025 Task 2: Reward-Selective Fine-Tuning based Code Generation Approach for Bangla Prompts
%A Farazi, Musa Tur
%A Reza, Nufayer Jahan
%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 farazi-reza-2025-troopers
%X We present a formally grounded description of a reward-selective fine-tuning (RSFT) pipeline for code generation from Bangla natural-language prompts. The implemented system mines candidate programs via temperature and nucleus sampling, executes candidates in a sandbox and retains programs that pass all unit tests, performs supervised fine-tuning (SFT) on winners using parameter-efficient Low rank adaptation (LoRA) adapters, and augments robustness through fuzzed asserts. We specify the exact objectives and estimators used, provide a Bangla-aware preprocessing recipe, prove simple properties of the sampling budget, and report an ablation showing the effect of inference sample budget K on accuracy. We also include a threat model for safe execution. Our codes are available on GitHub.
%U https://aclanthology.org/2025.banglalp-1.54/
%P 561-565
Markdown (Informal)
[Troopers at BLP-2025 Task 2: Reward-Selective Fine-Tuning based Code Generation Approach for Bangla Prompts](https://aclanthology.org/2025.banglalp-1.54/) (Farazi & Reza, BanglaLP 2025)
ACL