@inproceedings{singh-etal-2025-indic,
title = "{INDIC} {QA} {BENCHMARK}: A Multilingual Benchmark to Evaluate Question Answering capability of {LLM}s for {I}ndic Languages",
author = "Singh, Abhishek Kumar and
Kumar, Vishwajeet and
Murthy, Rudra and
Sen, Jaydeep and
Mittal, Ashish and
Ramakrishnan, Ganesh",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.141/",
doi = "10.18653/v1/2025.findings-naacl.141",
pages = "2607--2626",
ISBN = "979-8-89176-195-7",
abstract = "Large Language Models (LLMs) perform well on unseen tasks in English, but their abilities in non-English languages are less explored due to limited benchmarks and training data. To bridge this gap, we introduce the Indic-QA Benchmark, a large dataset for context-grounded question answering in 11 major Indian languages, covering both extractive and abstractive tasks. Evaluations of multilingual LLMs, including instruction fine-tuned versions, revealed weak performance in low-resource languages due to a strong English-language bias in their training data. We also investigated the Translate-Test paradigm,where inputs are translated to English for processing and the results are translated back into the source language for output. This approach outperformed multilingual LLMs, particularly in low-resource settings. By releasing Indic-QA, we aim to promote further research into LLMs' question-answering capabilities in low-resource languages. This benchmark offers a critical resource to address existing limitations and foster multilingual understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2025-indic">
<titleInfo>
<title>INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishwajeet</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudra</namePart>
<namePart type="family">Murthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaydeep</namePart>
<namePart type="family">Sen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ganesh</namePart>
<namePart type="family">Ramakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) perform well on unseen tasks in English, but their abilities in non-English languages are less explored due to limited benchmarks and training data. To bridge this gap, we introduce the Indic-QA Benchmark, a large dataset for context-grounded question answering in 11 major Indian languages, covering both extractive and abstractive tasks. Evaluations of multilingual LLMs, including instruction fine-tuned versions, revealed weak performance in low-resource languages due to a strong English-language bias in their training data. We also investigated the Translate-Test paradigm,where inputs are translated to English for processing and the results are translated back into the source language for output. This approach outperformed multilingual LLMs, particularly in low-resource settings. By releasing Indic-QA, we aim to promote further research into LLMs’ question-answering capabilities in low-resource languages. This benchmark offers a critical resource to address existing limitations and foster multilingual understanding.</abstract>
<identifier type="citekey">singh-etal-2025-indic</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.141</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.141/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2607</start>
<end>2626</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages
%A Singh, Abhishek Kumar
%A Kumar, Vishwajeet
%A Murthy, Rudra
%A Sen, Jaydeep
%A Mittal, Ashish
%A Ramakrishnan, Ganesh
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F singh-etal-2025-indic
%X Large Language Models (LLMs) perform well on unseen tasks in English, but their abilities in non-English languages are less explored due to limited benchmarks and training data. To bridge this gap, we introduce the Indic-QA Benchmark, a large dataset for context-grounded question answering in 11 major Indian languages, covering both extractive and abstractive tasks. Evaluations of multilingual LLMs, including instruction fine-tuned versions, revealed weak performance in low-resource languages due to a strong English-language bias in their training data. We also investigated the Translate-Test paradigm,where inputs are translated to English for processing and the results are translated back into the source language for output. This approach outperformed multilingual LLMs, particularly in low-resource settings. By releasing Indic-QA, we aim to promote further research into LLMs’ question-answering capabilities in low-resource languages. This benchmark offers a critical resource to address existing limitations and foster multilingual understanding.
%R 10.18653/v1/2025.findings-naacl.141
%U https://aclanthology.org/2025.findings-naacl.141/
%U https://doi.org/10.18653/v1/2025.findings-naacl.141
%P 2607-2626
Markdown (Informal)
[INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages](https://aclanthology.org/2025.findings-naacl.141/) (Singh et al., Findings 2025)
ACL