@inproceedings{haider-etal-2025-robustness,
title = "Robustness of {LLM}s to Transliteration Perturbations in {B}angla",
author = "Haider, Fabiha and
Ishmam, Md Farhan and
Shifat, Fariha Tanjim and
Adib, Md Tasmim Rahman and
Fahim, Md and
Bhuiyan, Md Farhad Alam",
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-1.27/",
pages = "338--346",
ISBN = "979-8-89176-314-2",
abstract = "Bangla text on the internet often appears in mixed scripts that combine native Bangla characters with their Romanized transliterations. To ensure practical usability, language models should be robust to naturally occurring script mixing. Our work investigates the robustness of current LLMs and Bangla language models under various transliteration-based textual perturbations, \textit{i.e.}, we augment portions of existing Bangla datasets using transliteration. Specifically, we replace words and sentences with their transliterated text to emulate realistic script mixing, and similarly, replace the top k salient words to emulate adversarial script mixing. Our experiments reveal interesting behavioral insights and vulnerabilities to robustness in language models for Bangla, which can be crucial for deploying such models in real-world scenarios and enhancing their overall robustness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haider-etal-2025-robustness">
<titleInfo>
<title>Robustness of LLMs to Transliteration Perturbations in Bangla</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fabiha</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Farhan</namePart>
<namePart type="family">Ishmam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fariha</namePart>
<namePart type="given">Tanjim</namePart>
<namePart type="family">Shifat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tasmim</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Adib</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>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Farhad</namePart>
<namePart type="given">Alam</namePart>
<namePart type="family">Bhuiyan</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>Bangla text on the internet often appears in mixed scripts that combine native Bangla characters with their Romanized transliterations. To ensure practical usability, language models should be robust to naturally occurring script mixing. Our work investigates the robustness of current LLMs and Bangla language models under various transliteration-based textual perturbations, i.e., we augment portions of existing Bangla datasets using transliteration. Specifically, we replace words and sentences with their transliterated text to emulate realistic script mixing, and similarly, replace the top k salient words to emulate adversarial script mixing. Our experiments reveal interesting behavioral insights and vulnerabilities to robustness in language models for Bangla, which can be crucial for deploying such models in real-world scenarios and enhancing their overall robustness.</abstract>
<identifier type="citekey">haider-etal-2025-robustness</identifier>
<location>
<url>https://aclanthology.org/2025.banglalp-1.27/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>338</start>
<end>346</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Robustness of LLMs to Transliteration Perturbations in Bangla
%A Haider, Fabiha
%A Ishmam, Md Farhan
%A Shifat, Fariha Tanjim
%A Adib, Md Tasmim Rahman
%A Fahim, Md
%A Bhuiyan, Md Farhad Alam
%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 haider-etal-2025-robustness
%X Bangla text on the internet often appears in mixed scripts that combine native Bangla characters with their Romanized transliterations. To ensure practical usability, language models should be robust to naturally occurring script mixing. Our work investigates the robustness of current LLMs and Bangla language models under various transliteration-based textual perturbations, i.e., we augment portions of existing Bangla datasets using transliteration. Specifically, we replace words and sentences with their transliterated text to emulate realistic script mixing, and similarly, replace the top k salient words to emulate adversarial script mixing. Our experiments reveal interesting behavioral insights and vulnerabilities to robustness in language models for Bangla, which can be crucial for deploying such models in real-world scenarios and enhancing their overall robustness.
%U https://aclanthology.org/2025.banglalp-1.27/
%P 338-346
Markdown (Informal)
[Robustness of LLMs to Transliteration Perturbations in Bangla](https://aclanthology.org/2025.banglalp-1.27/) (Haider et al., BanglaLP 2025)
ACL
- Fabiha Haider, Md Farhan Ishmam, Fariha Tanjim Shifat, Md Tasmim Rahman Adib, Md Fahim, and Md Farhad Alam Bhuiyan. 2025. Robustness of LLMs to Transliteration Perturbations in Bangla. In Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), pages 338–346, Mumbai, India. Association for Computational Linguistics.