{"total":25,"rows":[{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2204.08832","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","created":"2022-04-19","cited_by_count":62,"area":null},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"area":null},{"id":"2312.13951","title":"Typhoon: Thai Large Language Models","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2312.04649","title":"PyThaiNLP: Thai Natural Language Processing in Python","created":"2023-12-07","cited_by_count":28,"area":null},{"id":"2306.09572","title":"How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese","created":"2023-06-16","cited_by_count":20,"area":null},{"id":"2409.11501","title":"Egalitarian Language Representation in Language Models: It All Begins with Tokenizers","created":"2024-09-17","cited_by_count":20,"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":"2503.03862","title":"Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2403.11130","title":"Exploring Tokenization Strategies and Vocabulary Sizes for Enhanced Arabic Language Models","created":"2024-03-17","cited_by_count":5,"area":null},{"id":"2410.17532","title":"Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2508.15239","title":"WangchanThaiInstruct: An instruction-following Dataset for Culture-Aware, Multitask, and Multi-domain Evaluation in Thai","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2311.12475","title":"PhayaThaiBERT: Enhancing a Pretrained Thai Language Model with Unassimilated Loanwords","created":"2023-11-21","cited_by_count":2,"area":null},{"id":"2410.04795","title":"Representing the Under-Represented: Cultural and Core Capability Benchmarks for Developing Thai Large Language Models","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2507.14664","title":"Mangosteen: An Open Thai Corpus for Language Model Pretraining","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2206.09680","title":"Misspelling Semantics In Thai","created":"2022-06-20","cited_by_count":0,"area":null},{"id":"2310.12778","title":"Label-Aware Automatic Verbalizer for Few-Shot Text Classification","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2403.01817","title":"NusaBERT: Teaching IndoBERT to be Multilingual and Multicultural","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2405.07586","title":"Thai Universal Dependency Treebank","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2406.06000","title":"ThaiCoref: Thai Coreference Resolution Dataset","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2504.07858","title":"Empowering Global Voices: A Data-Efficient, Phoneme-Tone Adaptive Approach to High-Fidelity Speech Synthesis","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2505.24609","title":"Explainable Depression Detection using Masked Hard Instance Mining","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2511.13481","title":"Aspect-Level Obfuscated Sentiment in Thai Financial Disclosures and Its Impact on Abnormal Returns","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2609.27558","title":"ThaiTrees: Thai Syntactic Dependency Trees Across Domains","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.14980","title":"Single-Sample Decoding of a Two-Layer Sound-Word Canvas Model for Thai Klon Pad","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}