{"total":41,"rows":[{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2603.04964","title":"Replaying pre-training data improves fine-tuning","created":"2026-03-05","cited_by_count":13,"area":null},{"id":"2506.07597","title":"Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque","created":"2025-06-09","cited_by_count":12,"area":null},{"id":"2411.11171","title":"LL\\\"aMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch","created":"2024-11-17","cited_by_count":9,"area":null},{"id":"2502.02904","title":"ScholaWrite: A Dataset of End-to-End Scholarly Writing Process","created":"2025-02-05","cited_by_count":9,"area":null},{"id":"2506.03902","title":"The Harmonic Structure of Information Contours","created":"2025-06-04","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":"2505.02456","title":"Colombian Waitresses y Jueces canadienses: Gender and Country Biases in Occupation Recommendations from LLMs","created":"2025-05-05","cited_by_count":7,"area":null},{"id":"2502.09387","title":"Truth Knows No Language: Evaluating Truthfulness Beyond English","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2503.23542","title":"Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2504.16921","title":"IberBench: LLM Evaluation on Iberian Languages","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2506.00288","title":"Emergent Abilities of Large Language Models under Continued Pretraining for Language Adaptation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2506.04915","title":"A Practitioner's Guide to Building ASR Models for Low-Resource Languages: A Case Study on Scottish Gaelic","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2412.13922","title":"Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2412.14471","title":"Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2606.26158","title":"Life After Benchmark Saturation: A Case Study of CORE-Bench","created":"2026-06-23","cited_by_count":4,"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":"2406.11464","title":"Automating Easy Read Text Segmentation","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2406.13893","title":"Open Generative Large Language Models for Galician","created":"2024-06-19","cited_by_count":3,"area":null},{"id":"2410.18902","title":"LLMs for Extremely Low-Resource Finno-Ugric Languages","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2503.01611","title":"In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2512.10772","title":"Grow Up and Merge: Scaling Strategies for Efficient Language Adaptation","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2407.17479","title":"The #Somos600M Project: Generating NLP resources that represent the diversity of the languages from LATAM, the Caribbean, and Spain","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2506.15239","title":"Lost in Variation? Evaluating NLI Performance in Basque and Spanish Geographical Variants","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2507.00999","title":"La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America","created":"2025-07-01","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":"2510.21193","title":"Estonian Native Large Language Model Benchmark","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2510.22747","title":"Low-Resource Dialect Adaptation of Large Language Models: A French Dialect Case-Study","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2410.14765","title":"What's New in My Data? Novelty Exploration via Contrastive Generation","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2502.16961","title":"UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2504.03312","title":"Evaluating Compact LLMs for Zero-Shot Iberian Language Tasks on End-User Devices","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2603.02041","title":"EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2604.02135","title":"GaelEval: Benchmarking LLM Performance for Scottish Gaelic","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2503.01851","title":"Euskarazko lehen C1 ebaluatzaile automatikoa","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2512.03903","title":"BERnaT: Basque Encoders for Representing Natural Textual Diversity","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.08713","title":"Automatic Essay Scoring and Feedback Generation in Basque Language Learning","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2603.25189","title":"A Catalog of Basque Dialectal Resources: Online Collections and Standard-to-Dialectal Adaptations","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2603.28263","title":"Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2608.05850","title":"MameLoshnLM: Yiddish Language Model and Evaluation Benchmark","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.30609","title":"Reading the News: Adapting Large Language Models to Swedish Journalism Through Continued Pre-Training","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.03350","title":"From Zero to Hero: An Open LLM Ecosystem for Armenian","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}