{"total":17,"rows":[{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311,"area":null},{"id":"2403.06350","title":"IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages","created":"2024-03-11","cited_by_count":52,"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":"2408.11440","title":"LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systems","created":"2024-08-21","cited_by_count":10,"area":null},{"id":"2405.05572","title":"From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2403.13638","title":"Pretraining Language Models Using Translationese","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2509.11570","title":"Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges","created":"2025-09-15","cited_by_count":6,"area":null},{"id":"2512.10780","title":"Script Gap: Evaluating LLM Triage on Indian Languages in Native vs Romanized Scripts in a Real World Setting","created":"2025-12-11","cited_by_count":5,"area":null},{"id":"2501.05816","title":"IndoNLP 2025: Shared Task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2504.21540","title":"Improving Informally Romanized Language Identification","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2601.03194","title":"X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and A Novel LLM-consulted Explanation Framework","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2603.14053","title":"NepTam: A Nepali-Tamang Parallel Corpus and Baseline Machine Translation Experiments","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2402.04542","title":"Share What You Already Know: Cross-Language-Script Transfer and Alignment for Sentiment Detection in Code-Mixed Data","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2505.19851","title":"Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.11832","title":"ILID: Native Script Language Identification for Indian Languages","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2601.12389","title":"NADIR: Differential Attention Flow for Non-Autoregressive Transliteration in Indic Languages","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2606.30790","title":"Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions","created":"2026-06-29","cited_by_count":0,"area":null}],"next_cursor":null}