{"total":38,"rows":[{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2212.05409","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","created":"2022-12-11","cited_by_count":102,"area":null},{"id":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43,"area":null},{"id":"2203.05437","title":"IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages","created":"2022-03-10","cited_by_count":42,"area":null},{"id":"2205.11081","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","created":"2022-05-23","cited_by_count":42,"area":null},{"id":"2401.14280","title":"RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization","created":"2024-01-25","cited_by_count":29,"area":null},{"id":"2212.10180","title":"IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages","created":"2022-12-20","cited_by_count":27,"area":null},{"id":"2204.08776","title":"IndicXNLI: Evaluating Multilingual Inference for Indian Languages","created":"2022-04-19","cited_by_count":26,"area":null},{"id":"2305.08828","title":"PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2504.06011","title":"Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2305.05858","title":"V\\=arta: A Large-Scale Headline-Generation Dataset for Indic Languages","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2506.02280","title":"The State of Large Language Models for African Languages: Progress and Challenges","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2407.00416","title":"Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs","created":"2024-06-29","cited_by_count":7,"area":null},{"id":"2410.03576","title":"Table Question Answering for Low-resourced Indic Languages","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2502.20420","title":"Chitranuvad: Adapting Multi-Lingual LLMs for Multimodal Translation","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2311.17743","title":"Mukhyansh: A Headline Generation Dataset for Indic Languages","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2312.09508","title":"IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian Languages","created":"2023-12-15","cited_by_count":5,"area":null},{"id":"2305.13085","title":"Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2305.14004","title":"S\\={a}mayik: A Benchmark and Dataset for English-Sanskrit Translation","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2412.15248","title":"RoundTripOCR: A Data Generation Technique for Enhancing Post-OCR Error Correction in Low-Resource Devanagari Languages","created":"2024-12-14","cited_by_count":3,"area":null},{"id":"2303.16657","title":"Summarizing Indian Languages using Multilingual Transformers based Models","created":"2023-03-29","cited_by_count":2,"area":null},{"id":"2309.11259","title":"Sequence-to-Sequence Spanish Pre-trained Language Models","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2310.13228","title":"The Less the Merrier? Investigating Language Representation in Multilingual Models","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2407.04721","title":"AgriLLM: Harnessing Transformers for Farmer Queries","created":"2024-06-21","cited_by_count":2,"area":null},{"id":"2505.17102","title":"BanglaByT5: Byte-Level Modelling for Bangla","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2212.05702","title":"Implementing Deep Learning-Based Approaches for Article Summarization in Indian Languages","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2304.13005","title":"Evaluating Inter-Bilingual Semantic Parsing for Indian Languages","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2312.15181","title":"Multilingual Bias Detection and Mitigation for Indian Languages","created":"2023-12-23","cited_by_count":1,"area":null},{"id":"2409.13747","title":"Machine Translation with Large Language Models: Decoder Only vs. Encoder-Decoder","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2410.09184","title":"L3Cube-MahaSum: A Comprehensive Dataset and BART Models for Abstractive Text Summarization in Marathi","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2504.07989","title":"Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2305.12371","title":"Machine Translation by Projecting Text into the Same Phonetic-Orthographic Space Using a Common Encoding","created":"2023-05-21","cited_by_count":0,"area":null},{"id":"2510.07061","title":"Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.22160","title":"SentiMaithili: A Benchmark Dataset for Sentiment and Reason Generation for the Low-Resource Maithili Language","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2512.15226","title":"Yes-MT's Submission to the Low-Resource Indic Language Translation Shared Task in WMT 2024","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2603.18911","title":"Progressive Training for Explainable Citation-Grounded Dialogue: Reducing Hallucination to Zero in English-Hindi LLMs","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.19797","title":"Enhancing ASR Performance in the Medical Domain for Dravidian Languages","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.27050","title":"BhashaSetu: A Data-Centric Approach to Low-Resource Machine Translation","created":"2026-05-26","cited_by_count":0,"area":null}],"next_cursor":null}