# IndicGenBench XQuAD-IN: Extractive Question Answering Translated into Indic Languages (Google Research)

## Facts

- Provider: Google Research (Singh et al.)
- License: CC-BY-SA-4.0 (https://github.com/google-research-datasets/indic-gen-bench)
- Size: 41 files
- Format: JSON (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/google/IndicGenBench_xquad_in
- Access: public, readable without an account
- Category: Natural Language Processing
- Source: https://arxiv.org/abs/2404.16816
- Page: https://scigantic.com/archive/9464974e-012d-59d4-a4b1-3cf2c0f20154
- Keywords: Natural Language Processing, benchmark, JSON, Hugging Face

## About

XQuAD-IN is IndicGenBench's multilingual question answering task: the XQuAD paragraphs, questions and answers (themselves drawn from SQuAD) translated by humans into Indic languages, so a model must read a passage in the target language and generate or extract the answer. IndicGenBench is a multilingual, multi-way parallel benchmark from Google Research for measuring language generation by large language models in 29 Indic languages spanning 13 writing scripts and 4 language families, including many low-resource languages such as Assamese, Bhojpuri, Awadhi, Maithili, Santali and Konkani alongside Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada and Malayalam. Google extended existing English benchmarks by collecting human translations of their English examples into each target language. The repository holds 39 JSON files, split by language and train, dev and test, named like xquad_ta_test.json (about 47 MB in total). Load with the Hugging Face datasets library or plain JSON readers. It is used to evaluate reading comprehension and grounded answer generation of large language models in South Asian languages. Distributed under CC BY-SA 4.0, following the XQuAD source license; cite Singh et al., IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages, ACL 2024.

## Load the data

```python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="google/IndicGenBench_xquad_in", filename="xquad_as_dev.json", repo_type="dataset")
print(path)
```

## Data structure

File types in sampled files: JSON

Example file: `xquad_as_dev.json`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/9464974e-012d-59d4-a4b1-3cf2c0f20154
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/9464974e-012d-59d4-a4b1-3cf2c0f20154
- Over MCP: `get_schema_card` with id `9464974e-012d-59d4-a4b1-3cf2c0f20154` at https://api.scigantic.com/mcp

## Related topics

- [JSON datasets](https://scigantic.com/topics/json)
- [Benchmark datasets](https://scigantic.com/topics/benchmark)
- [Natural Language Processing datasets](https://scigantic.com/topics/natural-language-processing)
