mlsanityData to 7 Oct 2026

IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages

arXiv 2203.05437 ↗First posted 10 Mar 2022cs.CL cs.AIcited by 42

Not on the map. Why?

Abstract (arXiv)

Natural Language Generation (NLG) for non-English languages is hampered by the scarcity of datasets in these languages. In this paper, we present the IndicNLG Benchmark, a collection of datasets for benchmarking NLG for 11 Indic languages. We focus on five diverse tasks, namely, biography generation using Wikipedia infoboxes, news headline generation, sentence summarization, paraphrase generation and, question generation. We describe the created datasets and use them to benchmark the performance of several monolingual and multilingual baselines that leverage pre-trained sequence-to-sequence models. Our results exhibit the strong performance of multilingual language-specific pre-trained models, and the utility of models trained on our dataset for other related NLG tasks. Our dataset creation methods can be easily applied to modest-resource languages as they involve simple steps such as scraping news articles and Wikipedia infoboxes, light cleaning, and pivoting through machine translation data. To the best of our knowledge, the IndicNLG Benchmark is the first NLG benchmark for Indic languages and the most diverse multilingual NLG dataset, with approximately 8M examples across 5 tasks and 11 languages. The datasets and models are publicly available at https://ai4bharat.iitm.ac.in/indicnlg-suite.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 34 of its 65 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

34 of 65 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  5. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  6. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  7. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  8. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  9. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 998
  10. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  11. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 575
  12. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 486
22 more
  1. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  2. 2021XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languagescited by 346
  3. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 339
  4. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  5. 2021The GEM Benchmark: Natural Language Generation, its Evaluation and Metricscited by 239
  6. 2017Challenges in Data-to-Document Generationcited by 226
  7. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  8. 2017Learning to Ask: Neural Question Generation for Reading Comprehensioncited by 186
  9. 2020WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarizationcited by 154
  10. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 144
  11. 2021Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languagescited by 133
  12. 2020MLSUM: The Multilingual Summarization Corpuscited by 121
  13. 2020Text-to-Text Pre-Training for Data-to-Text Taskscited by 104
  14. 2019Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challengecited by 86
  15. 2017Neural Question Generation from Text: A Preliminary Studycited by 78
  16. 2021IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generationcited by 57
  17. 2021IndicBART: A Pre-trained Model for Indic Natural Language Generationcited by 39
  18. 2021Data-to-text Generation with Macro Planningcited by 34
  19. 2018Open Subtitles Paraphrase Corpus for Six Languagescited by 24
  20. 2021LOT: A Story-Centric Benchmark for Evaluating Chinese Long Text Understanding and Generationcited by 24
  21. 2021Factorising Meaning and Form for Intent-Preserving Paraphrasingcited by 22
  22. 2021YANMTT: Yet Another Neural Machine Translation Toolkitcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 9; 2024: 16; 2025: 13; 2026: 2.

42 papers.

Sort:

By area:

  1. 2024LLMs Are Few-Shot In-Context Low-Resource Language Learnerscited by 68
  2. 2024IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languagescited by 55
  3. 2024SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languagescited by 41
  4. 2022NusaCrowd: Open Source Initiative for Indonesian NLP Resourcescited by 38
  5. 2024PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Datacited by 37
  6. 2024Airavata: Introducing Hindi Instruction-tuned LLMcited by 32
  7. 2024RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanizationcited by 29
  8. 2022Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languagescited by 28
  9. 2024Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpuscited by 24
  10. 2023BenLLMEval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLPcited by 23
  11. 2023Dolphin: A Challenging and Diverse Benchmark for Arabic NLGcited by 22
  12. 2023InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuningcited by 21
30 more
  1. 2024Cheetah: Natural Language Generation for 517 African Languagescited by 15
  2. 2024mEdIT: Multilingual Text Editing via Instruction Tuningcited by 13
  3. 2023PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in Indiacited by 11
  4. 2025One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizerscited by 11
  5. 2024Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languagescited by 10
  6. 2025Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindicited by 10
  7. 2025IndicMMLU-Pro: Benchmarking Indic Large Language Models on Multi-Task Language Understandingcited by 9
  8. 2025Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignmentcited by 9
  9. 2023V=arta: A Large-Scale Headline-Generation Dataset for Indic Languagescited by 8
  10. 2024LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in Englishcited by 7
  11. 2024Pretraining Language Models Using Translationesecited by 6
  12. 2025Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challengescited by 6
  13. 2023Mukhyansh: A Headline Generation Dataset for Indic Languagescited by 5
  14. 2025Script Gap: Evaluating LLM Triage on Indian Languages in Native vs Romanized Scripts in a Real World Settingcited by 5
  15. 2023NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languagescited by 4
  16. 2024Decoding the Diversity: A Review of the Indic AI Research Landscapecited by 4
  17. 2024Building pre-train LLM Dataset for the INDIC Languages: a case study on Hindicited by 4
  18. 2025A survey of diversity quantification in natural language processing: The why, what, where and howcited by 4
  19. 2023The Obscure Limitation of Modular Multilingual Language Modelscited by 3
  20. 2025Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languagescited by 3
  21. 2024IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?cited by 2
  22. 2025COSMMIC: Comment-Sensitive Multimodal Multilingual Indian Corpus for Summarization and Headline Generationcited by 2
  23. 2025IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languagescited by 2
  24. 2025Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?cited by 1
  25. 2025CRaFT: An Explanation-Based Framework for Evaluating Cultural Reasoning in Multilingual Language Modelscited by 1
  26. 2025PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generationcited by 1
  27. 2023Automatic Data Retrieval for Cross Lingual Summarizationcited by 0
  28. 2024Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferencescited by 0
  29. 2026INDIC DIALECT: A Multi Task Benchmark to Evaluate and Translate in Indian Language Dialectscited by 0
  30. 2026SurakshaEval: An Indic Safety Benchmark for Multilingual LLMscited by 0