Saved in:
Bibliographic Details
Main Authors: Prasanjith, Pasunuti, More, Prathmesh B, Kunchukuttan, Anoop, Dabre, Raj
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.01615
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913871849062400
author Prasanjith, Pasunuti
More, Prathmesh B
Kunchukuttan, Anoop
Dabre, Raj
author_facet Prasanjith, Pasunuti
More, Prathmesh B
Kunchukuttan, Anoop
Dabre, Raj
contents Retrieval-Augmented Generation (RAG) systems enable language models to access relevant information and generate accurate, well-grounded, and contextually informed responses. However, for Indian languages, the development of high-quality RAG systems is hindered by the lack of two critical resources: (1) evaluation benchmarks for retrieval and generation tasks, and (2) large-scale training datasets for multilingual retrieval. Most existing benchmarks and datasets are centered around English or high-resource languages, making it difficult to extend RAG capabilities to the diverse linguistic landscape of India. To address the lack of evaluation benchmarks, we create IndicMSMarco, a multilingual benchmark for evaluating retrieval quality and response generation in 13 Indian languages, created via manual translation of 1000 diverse queries from MS MARCO-dev set. To address the need for training data, we build a large-scale dataset of (question, answer, relevant passage) tuples derived from the Wikipedias of 19 Indian languages using state-of-the-art LLMs. Additionally, we include translated versions of the original MS MARCO dataset to further enrich the training data and ensure alignment with real-world information-seeking tasks. Resources are available here: https://huggingface.co/collections/ai4bharat/indicragsuite-683e7273cb2337208c8c0fcb
format Preprint
id arxiv_https___arxiv_org_abs_2506_01615
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IndicRAGSuite: Large-Scale Datasets and a Benchmark for Indian Language RAG Systems
Prasanjith, Pasunuti
More, Prathmesh B
Kunchukuttan, Anoop
Dabre, Raj
Computation and Language
Retrieval-Augmented Generation (RAG) systems enable language models to access relevant information and generate accurate, well-grounded, and contextually informed responses. However, for Indian languages, the development of high-quality RAG systems is hindered by the lack of two critical resources: (1) evaluation benchmarks for retrieval and generation tasks, and (2) large-scale training datasets for multilingual retrieval. Most existing benchmarks and datasets are centered around English or high-resource languages, making it difficult to extend RAG capabilities to the diverse linguistic landscape of India. To address the lack of evaluation benchmarks, we create IndicMSMarco, a multilingual benchmark for evaluating retrieval quality and response generation in 13 Indian languages, created via manual translation of 1000 diverse queries from MS MARCO-dev set. To address the need for training data, we build a large-scale dataset of (question, answer, relevant passage) tuples derived from the Wikipedias of 19 Indian languages using state-of-the-art LLMs. Additionally, we include translated versions of the original MS MARCO dataset to further enrich the training data and ensure alignment with real-world information-seeking tasks. Resources are available here: https://huggingface.co/collections/ai4bharat/indicragsuite-683e7273cb2337208c8c0fcb
title IndicRAGSuite: Large-Scale Datasets and a Benchmark for Indian Language RAG Systems
topic Computation and Language
url https://arxiv.org/abs/2506.01615