@inproceedings{tran-etal-2026-representation,
title = "Representation-Aware Prompting for Zero-Shot {M}arathi Text Classification: {IPA}, {R}omanization, Repetition",
author = "Tran, Van-Hien and
Vu, Huy Hien and
Tanaka, Hideki and
Utiyama, Masao",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Plum, Alistair and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the Second Workshop on Language Models for Low-Resource Languages ({L}o{R}es{LM} 2026)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.loreslm-1.37/",
pages = "436--443",
ISBN = "979-8-89176-377-7",
abstract = "Large language models (LLMs) often underperform in zero-shot text classification for low-resource, non-Latin languages due to script and tokenization mismatches. We propose \textit{representation-aware prompting} for Marathi that augments the original script with International Phonetic Alphabet (IPA) transcriptions, romanization, or a repetition-based fallback when external converters are unavailable. Experiments with two instruction-tuned LLMs on Marathi sentiment analysis and hate detection show consistent gains over script-only prompting (up to +2.6 accuracy points). We further find that the most effective augmentation is model-dependent, and that combining all variants is not consistently beneficial, suggesting that concise, targeted cues are preferable in zero-shot settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2026-representation">
<titleInfo>
<title>Representation-Aware Prompting for Zero-Shot Marathi Text Classification: IPA, Romanization, Repetition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Van-Hien</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huy</namePart>
<namePart type="given">Hien</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Tanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-377-7</identifier>
</relatedItem>
<abstract>Large language models (LLMs) often underperform in zero-shot text classification for low-resource, non-Latin languages due to script and tokenization mismatches. We propose representation-aware prompting for Marathi that augments the original script with International Phonetic Alphabet (IPA) transcriptions, romanization, or a repetition-based fallback when external converters are unavailable. Experiments with two instruction-tuned LLMs on Marathi sentiment analysis and hate detection show consistent gains over script-only prompting (up to +2.6 accuracy points). We further find that the most effective augmentation is model-dependent, and that combining all variants is not consistently beneficial, suggesting that concise, targeted cues are preferable in zero-shot settings.</abstract>
<identifier type="citekey">tran-etal-2026-representation</identifier>
<location>
<url>https://aclanthology.org/2026.loreslm-1.37/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>436</start>
<end>443</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Representation-Aware Prompting for Zero-Shot Marathi Text Classification: IPA, Romanization, Repetition
%A Tran, Van-Hien
%A Vu, Huy Hien
%A Tanaka, Hideki
%A Utiyama, Masao
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Plum, Alistair
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-377-7
%F tran-etal-2026-representation
%X Large language models (LLMs) often underperform in zero-shot text classification for low-resource, non-Latin languages due to script and tokenization mismatches. We propose representation-aware prompting for Marathi that augments the original script with International Phonetic Alphabet (IPA) transcriptions, romanization, or a repetition-based fallback when external converters are unavailable. Experiments with two instruction-tuned LLMs on Marathi sentiment analysis and hate detection show consistent gains over script-only prompting (up to +2.6 accuracy points). We further find that the most effective augmentation is model-dependent, and that combining all variants is not consistently beneficial, suggesting that concise, targeted cues are preferable in zero-shot settings.
%U https://aclanthology.org/2026.loreslm-1.37/
%P 436-443
Markdown (Informal)
[Representation-Aware Prompting for Zero-Shot Marathi Text Classification: IPA, Romanization, Repetition](https://aclanthology.org/2026.loreslm-1.37/) (Tran et al., LoResLM 2026)
ACL