{"total":105,"rows":[{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"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":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"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":"2212.09535","title":"BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting","created":"2022-12-19","cited_by_count":90,"area":null},{"id":"2204.13509","title":"On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model","created":"2022-04-28","cited_by_count":81,"area":null},{"id":"2109.04650","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","created":"2021-09-10","cited_by_count":76,"area":null},{"id":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68,"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":"2210.08750","title":"Keep Me Updated! Memory Management in Long-term Conversations","created":"2022-10-17","cited_by_count":63,"area":null},{"id":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2403.11009","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","created":"2024-03-16","cited_by_count":50,"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":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44,"area":null},{"id":"2107.07498","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","created":"2021-07-15","cited_by_count":41,"area":null},{"id":"2210.12391","title":"MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition","created":"2022-10-22","cited_by_count":38,"area":null},{"id":"2204.04541","title":"KOBEST: Korean Balanced Evaluation of Significant Tasks","created":"2022-04-09","cited_by_count":37,"area":null},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2211.15649","title":"Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2305.17701","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","created":"2023-05-28","cited_by_count":24,"area":null},{"id":"2203.01552","title":"Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking","created":"2022-03-03","cited_by_count":21,"area":null},{"id":"2110.06744","title":"Masader: Metadata Sourcing for Arabic Text and Speech Data Resources","created":"2021-10-13","cited_by_count":20,"area":null},{"id":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","cited_by_count":14,"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":"2403.10882","title":"Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Korean","created":"2024-03-16","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":"2112.03204","title":"Quantifying Adaptability in Pre-trained Language Models with 500 Tasks","created":"2021-12-06","cited_by_count":13,"area":null},{"id":"2211.13112","title":"This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish","created":"2022-11-23","cited_by_count":13,"area":null},{"id":"2505.21265","title":"Multilingual Pretraining for Pixel Language Models","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2202.13558","title":"CINO: A Chinese Minority Pre-trained Language Model","created":"2022-02-28","cited_by_count":11,"area":null},{"id":"2112.07522","title":"LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2305.14716","title":"GlobalBench: A Benchmark for Global Progress in Natural Language Processing","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2209.04126","title":"MaxMatch-Dropout: Subword Regularization for WordPiece","created":"2022-09-09","cited_by_count":8,"area":null},{"id":"2403.15882","title":"VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding","created":"2024-03-23","cited_by_count":8,"area":null},{"id":"2508.16431","title":"Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish","created":"2025-08-22","cited_by_count":8,"area":null},{"id":"2202.01764","title":"JaQuAD: Japanese Question Answering Dataset for Machine Reading Comprehension","created":"2022-02-03","cited_by_count":7,"area":null},{"id":"2301.03136","title":"Removing Non-Stationary Knowledge From Pre-Trained Language Models for Entity-Level Sentiment Classification in Finance","created":"2023-01-09","cited_by_count":7,"area":null},{"id":"2307.04285","title":"HistRED: A Historical Document-Level Relation Extraction Dataset","created":"2023-07-10","cited_by_count":7,"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":"2506.08400","title":"mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2204.04873","title":"Adapting BigScience Multilingual Model to Unseen Languages","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2305.13026","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2407.09184","title":"Does Incomplete Syntax Influence Korean Language Model? Focusing on Word Order and Case Markers","created":"2024-07-12","cited_by_count":6,"area":null},{"id":"2309.10661","title":"NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages","created":"2023-09-19","cited_by_count":5,"area":null},{"id":"2210.11870","title":"LittleBird: Efficient Faster & Longer Transformer for Question Answering","created":"2022-10-21","cited_by_count":4,"area":null},{"id":"2306.02349","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2310.15541","title":"Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2410.08731","title":"Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2412.00856","title":"K-UD: Revising Korean Universal Dependencies Guidelines","created":"2024-12-01","cited_by_count":4,"area":null},{"id":"2112.01624","title":"A Survey on Awesome Korean NLP Datasets","created":"2021-10-17","cited_by_count":3,"area":null},{"id":"2305.06330","title":"Korean Named Entity Recognition Based on Language-Specific Features","created":"2023-05-10","cited_by_count":3,"area":null},{"id":"2306.12089","title":"Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints","created":"2023-06-21","cited_by_count":3,"area":null},{"id":"2506.21508","title":"skLEP: A Slovak General Language Understanding Benchmark","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2206.04935","title":"Sort by Structure: Language Model Ranking as Dependency Probing","created":"2022-06-10","cited_by_count":2,"area":null},{"id":"2301.08145","title":"Music Playlist Title Generation Using Artist Information","created":"2023-01-14","cited_by_count":2,"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":"2311.10922","title":"Explainable Product Classification for Customs","created":"2023-11-18","cited_by_count":2,"area":null},{"id":"2402.14428","title":"KoCoSa: Korean Context-aware Sarcasm Detection Dataset","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2402.17377","title":"KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue Benchmark","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2403.15467","title":"Don't be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks","created":"2024-03-20","cited_by_count":2,"area":null},{"id":"2502.15902","title":"IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2505.15261","title":"AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detection","created":"2025-05-21","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":"2210.06828","title":"Rethinking Annotation: Can Language Learners Contribute?","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2211.07713","title":"How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2302.04465","title":"Detecting Contextomized Quotes in News Headlines by Contrastive Learning","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2306.09752","title":"Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models","created":"2023-06-16","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":"2404.01140","title":"KoCoNovel: Annotated Dataset of Character Coreference in Korean Novels","created":"2024-04-01","cited_by_count":1,"area":null},{"id":"2406.08796","title":"Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2412.03784","title":"Speech Recognition-based Feature Extraction for Enhanced Automatic Severity Classification in Dysarthric Speech","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2505.09286","title":"A Scalable Unsupervised Framework for multi-aspect labeling of Multilingual and Multi-Domain Review Data","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2507.11049","title":"Journalism-Guided Agentic In-Context Learning for News Stance Detection","created":"2025-07-15","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":"2509.25918","title":"Bringing Emerging Architectures to Sequence Labeling in NLP","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2209.06422","title":"Language Chameleon: Transformation analysis between languages using Cross-lingual Post-training based on Pre-trained language models","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2210.02351","title":"Schema Encoding for Transferable Dialogue State Tracking","created":"2022-10-05","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":"2403.16444","title":"KIT-19: A Comprehensive Korean Instruction Toolkit on 19 Tasks for Fine-Tuning Korean Large Language Models","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2404.11539","title":"Evaluating Span Extraction in Generative Paradigm: A Reflection on Aspect-Based Sentiment Analysis","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2406.07922","title":"Automated Information Extraction from Thyroid Operation Narrative: A Comparative Study of GPT-4 and Fine-tuned KoELECTRA","created":"2024-06-12","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":"2410.14289","title":"SwaQuAD-24: QA Benchmark Dataset in Swahili","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2503.18250","title":"PAD: Towards Efficient Data Generation for Transfer Learning Using Phrase Alignment","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2503.18603","title":"LANGALIGN: Enhancing Non-English Language Models via Cross-Lingual Embedding Alignment","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2505.21380","title":"PHISH in MESH: Korean Adversarial Phonetic Substitution and Phonetic-Semantic Feature Integration Defense","created":"2025-05-27","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":"2507.04018","title":"Handling Korean Out-of-Vocabulary Words with Phoneme Representation Learning","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2507.04329","title":"No Language Data Left Behind: A Comparative Study of CJK Language Datasets in the Hugging Face Ecosystem","created":"2025-07-06","cited_by_count":0,"area":null},{"id":"2508.01486","title":"Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2510.20670","title":"\\textsc{CantoNLU}: A benchmark for Cantonese natural language understanding","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2603.03652","title":"Linguistically Informed Graph Model and Semantic Contrastive Learning for Korean Short Text Classification","created":"2026-03-04","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":"2605.30545","title":"Refining Word-Based Grammatical Error Annotation for L2 Korean","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.12433","title":"Marginal Alignment Does Not Guarantee Joint-Distribution Fidelity: An Official-Reference Audit of Nemotron-Personas-Korea with Cross-Locale Replication","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.22785","title":"Cross-National Information Attacks: A Two-Decade Analysis of Troll Behavior in Korea","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.03681","title":"Annotating Korean adnominal ending constructions in corpus data: Beyond relative-clause identification","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.20442","title":"Naver-News-KO: A Korean News Summarization Dataset for Open-Source Fine-Tuning of Summarization Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2608.27035","title":"Representing and Parsing Korean Constituency Structure at Different Levels of Granularity","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":"100"}