{"total":17,"rows":[{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"area":null},{"id":"2208.10684","title":"K-MHaS: A Multi-label Hate Speech Detection Dataset in Korean Online News Comment","created":"2022-08-23","cited_by_count":13,"area":null},{"id":"2103.13799","title":"Bertinho: Galician BERT Representations","created":"2021-03-25","cited_by_count":7,"area":null},{"id":"2108.09814","title":"UzBERT: pretraining a BERT model for Uzbek","created":"2021-08-22","cited_by_count":5,"area":null},{"id":"2310.04313","title":"KoMultiText: Large-Scale Korean Text Dataset for Classifying Biased Speech in Real-World Online Services","created":"2023-10-06","cited_by_count":3,"area":null},{"id":"2311.03928","title":"Improving Korean NLP Tasks with Linguistically Informed Subword Tokenization and Sub-character Decomposition","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2311.01712","title":"A New Korean Text Classification Benchmark for Recognizing the Political Intents in Online Newspapers","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2112.00567","title":"DPRK-BERT: The Supreme Language Model","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2307.09014","title":"Exploring acceptance of autonomous vehicle policies using KeyBERT and SNA: Targeting engineering students","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2309.10339","title":"KoBigBird-large: Transformation of Transformer for Korean Language Understanding","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2402.15046","title":"CARBD-Ko: A Contextually Annotated Review Benchmark Dataset for Aspect-Level Sentiment Classification in Korean","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2403.16158","title":"Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2409.00158","title":"Developing an End-to-End Framework for Predicting the Social Communication Severity Scores of Children with Autism Spectrum Disorder","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2412.11671","title":"BioBridge: Unified Bio-Embedding with Bridging Modality in Code-Switched EMR","created":"2024-12-16","cited_by_count":0,"area":null},{"id":"2509.22041","title":"Taxonomy of Comprehensive Safety for Clinical Agents","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2606.20089","title":"IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources","created":"2026-06-18","cited_by_count":0,"area":null}],"next_cursor":null}