{"total":36,"rows":[{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2402.11548","title":"KMMLU: Measuring Massive Multitask Language Understanding in Korean","created":"2024-02-18","cited_by_count":91,"area":null},{"id":"2109.05704","title":"Mitigating Language-Dependent Ethnic Bias in BERT","created":"2021-09-13","cited_by_count":87,"area":null},{"id":"2403.06412","title":"CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean","created":"2024-03-11","cited_by_count":66,"area":null},{"id":"2212.10758","title":"ORCA: A Challenging Benchmark for Arabic Language Understanding","created":"2022-12-21","cited_by_count":47,"area":null},{"id":"2309.02706","title":"HAE-RAE Bench: Evaluation of Korean Knowledge in Language Models","created":"2023-09-06","cited_by_count":47,"area":null},{"id":"2204.04541","title":"KOBEST: Korean Balanced Evaluation of Significant Tasks","created":"2022-04-09","cited_by_count":37,"area":null},{"id":"2304.00906","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","created":"2023-04-03","cited_by_count":16,"area":null},{"id":"2208.04826","title":"Compositional Evaluation on Japanese Textual Entailment and Similarity","created":"2022-08-09","cited_by_count":14,"area":null},{"id":"2108.06665","title":"Accurate, yet inconsistent? Consistency Analysis on Language Understanding Models","created":"2021-08-15","cited_by_count":13,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2101.11363","title":"KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding","created":"2021-01-27","cited_by_count":9,"area":null},{"id":"2101.10649","title":"Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks","created":"2021-01-26","cited_by_count":8,"area":null},{"id":"2403.17528","title":"Multilingual Sentence-T5: Scalable Sentence Encoders for Multilingual Applications","created":"2024-03-26","cited_by_count":7,"area":null},{"id":"2405.19795","title":"SLM as Guardian: Pioneering AI Safety with Small Language Models","created":"2024-05-30","cited_by_count":7,"area":null},{"id":"2305.06545","title":"GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2112.01624","title":"A Survey on Awesome Korean NLP Datasets","created":"2021-10-17","cited_by_count":3,"area":null},{"id":"2210.03068","title":"InferES : A Natural Language Inference Corpus for Spanish Featuring Negation-Based Contrastive and Adversarial Examples","created":"2022-10-06","cited_by_count":3,"area":null},{"id":"2402.13130","title":"Are ELECTRA's Sentence Embeddings Beyond Repair? The Case of Semantic Textual Similarity","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2404.06996","title":"XNLIeu: a dataset for cross-lingual NLI in Basque","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2105.00648","title":"A novel hybrid methodology of measuring sentence similarity","created":"2021-05-03","cited_by_count":2,"area":null},{"id":"2407.14878","title":"Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment","created":"2024-07-20","cited_by_count":2,"area":null},{"id":"2112.03014","title":"Transformer-based Korean Pretrained Language Models: A Survey on Three Years of Progress","created":"2021-11-25","cited_by_count":1,"area":null},{"id":"2301.08193","title":"JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its Applications","created":"2023-01-19","cited_by_count":1,"area":null},{"id":"2403.05257","title":"Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2503.09094","title":"Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2507.20419","title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2605.00116","title":"ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2109.08814","title":"Structured Pattern Pruning Using Regularization","created":"2021-09-18","cited_by_count":0,"area":null},{"id":"2112.00567","title":"DPRK-BERT: The Supreme Language Model","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2204.03831","title":"Marvelous Agglutinative Language Effect on Cross Lingual Transfer Learning","created":"2022-04-08","cited_by_count":0,"area":null},{"id":"2311.13784","title":"DaG LLM ver 1.0: Pioneering Instruction-Tuned Language Modeling for Korean NLP","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2507.03378","title":"Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2604.12377","title":"SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.23948","title":"KOMBO: Korean Character Representations Based on the Combination Rules of Subcharacters","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.03284","title":"SEA-NLI: Natural Language Inference as a Lens into Southeast Asian Cultural Understanding","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":null}