{"total":27,"rows":[{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152,"area":null},{"id":"2404.16816","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","created":"2024-04-25","cited_by_count":56,"area":null},{"id":"2304.08865","title":"Romanization-based Large-scale Adaptation of Multilingual Language Models","created":"2023-04-18","cited_by_count":21,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2309.06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","created":"2023-09-12","cited_by_count":18,"area":null},{"id":"2504.16977","title":"Tokenization Matters: Improving Zero-Shot NER for Indic Languages","created":"2025-04-23","cited_by_count":12,"area":null},{"id":"2505.21265","title":"Multilingual Pretraining for Pixel Language Models","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2305.07491","title":"A Comprehensive Analysis of Adapter Efficiency","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2406.17377","title":"A Three-Pronged Approach to Cross-Lingual Adaptation with Multilingual LLMs","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2510.07000","title":"Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languages","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2405.04829","title":"Fine-tuning Pre-trained Named Entity Recognition Models For Indian Languages","created":"2024-05-08","cited_by_count":2,"area":null},{"id":"2410.02611","title":"IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?","created":"2024-10-03","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":"2410.09192","title":"Long Range Named Entity Recognition for Marathi Documents","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2502.04245","title":"TriNER: A Series of Named Entity Recognition Models For Hindi, Bengali & Marathi","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2511.00486","title":"Leveraging the Cross-Domain & Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpus","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2512.01852","title":"BHRAM-IL: A Benchmark for Hallucination Recognition and Assessment in Multiple Indian Languages","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2605.22487","title":"Polite on the Surface, Broken in Practice: A Curated Dataset for Fixing Generation and Register Failures in Low-Resource Bangla Text Generation","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2505.16814","title":"Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2509.01147","title":"Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective","created":"2025-09-01","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":"2601.10161","title":"AWED-PIPER: Agents, Web Applications & Expert Detectors for Personally Identifiable Information Protection & Fine-grained Named Entity Recognition across 36 languages for 6.6 Billion Speakers","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.10388","title":"INDIC DIALECT: A Multi Task Benchmark to Evaluate and Translate in Indian Language Dialects","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.05599","title":"BhashaSetu: Cross-Lingual Knowledge Transfer from High-Resource to Extreme Low-Resource Languages","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2608.03105","title":"HomoEnsNER: Does Language Alignment Outperform Architectural Complexity in Gujarati Named Entity Recognition?","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.29682","title":"Named Entity Recognition using Sliding Window Approach","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}