{"total":23,"rows":[{"id":"2503.07920","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2503.12440","title":"HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs","created":"2025-03-16","cited_by_count":8,"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":"2509.24506","title":"Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2511.03237","title":"MUTANT: A Recipe for Multilingual Tokenizer Design","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2508.16185","title":"ParamBench: A Graduate-Level Benchmark for Evaluating LLM Understanding on Indic Subjects","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2512.00333","title":"IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2601.15550","title":"Common to Whom? Regional Cultural Commonsense and LLM Bias in India","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2508.19831","title":"Benchmarking Hindi LLMs: A New Suite of Datasets and a Comparative Analysis","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2512.01077","title":"ELR-1000: A Community-Generated Dataset for Endangered Indic Indigenous Languages","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2504.20022","title":"Better To Ask in English? Evaluating Factual Accuracy of Multilingual LLMs in English and Low-Resource Languages","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2508.02635","title":"Test Set Quality in Multilingual LLM Evaluation","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2507.01853","title":"Eka-Eval: An Evaluation Framework for Low-Resource Multilingual Large Language Models","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2508.03719","title":"Intent Aware Context Retrieval for Multi-Turn Agricultural Question Answering","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.13526","title":"MATA: Mindful Assessment of the Telugu Abilities of Large Language Models","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2605.28163","title":"DEPART: DEcomposing PARiTy across Multilingual LLMs","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.07167","title":"UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.07422","title":"The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2608.03494","title":"Beyond Initialization Loss: A Systematic Study of Token Embedding Initialization Strategies for LLM Vocabulary Extension","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.15535","title":"L3Cube-IndicQuest v2: A Large-Scale Multilingual Benchmark for Evaluating Factual Knowledge of Large Language Models Across Indic Languages","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.29167","title":"IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.15373","title":"In-Place Indic Tokenizer Expansion and Continual Pretraining of Nemotron-3-Nano-30B-A3B","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}