INDIC QA BENCHMARK: A Multilingual Benchmark to Evaluate Question Answering capability of LLMs for Indic Languages

TL;DR

The paper introduces the Indic QA Benchmark, a comprehensive dataset for evaluating multilingual question answering in 11 Indian languages, highlighting challenges and proposing translation-based methods to improve LLM performance in low-resource languages.

Contribution

It presents the Indic QA Benchmark dataset and analyzes LLM performance across Indian languages, revealing language bias issues and demonstrating the effectiveness of translation-based approaches.

Findings

Weak LLM performance in low-resource languages due to English bias

Translation test approach outperforms direct multilingual LLMs in low-resource settings

Benchmark promotes research on multilingual question answering in Indic languages

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 finetuned 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.