{"total":24,"rows":[{"id":"2311.00176","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","created":"2023-10-31","cited_by_count":174,"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":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66,"area":null},{"id":"2207.06991","title":"Language Modelling with Pixels","created":"2022-07-14","cited_by_count":55,"area":null},{"id":"2212.09648","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources","created":"2022-12-19","cited_by_count":38,"area":null},{"id":"2406.11477","title":"How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2404.06138","title":"Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages","created":"2024-04-09","cited_by_count":18,"area":null},{"id":"2310.11166","title":"ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2404.05829","title":"SambaLingo: Teaching Large Language Models New Languages","created":"2024-04-08","cited_by_count":11,"area":null},{"id":"2402.02113","title":"Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon","created":"2024-02-03","cited_by_count":7,"area":null},{"id":"2505.20133","title":"Token Distillation: Attention-aware Input Embeddings For New Tokens","created":"2025-05-26","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":"2409.08564","title":"Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia","created":"2024-09-13","cited_by_count":4,"area":null},{"id":"2503.01493","title":"Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced Setting","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2207.10524","title":"NusaCrowd: A Call for Open and Reproducible NLP Research in Indonesian Languages","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2504.17025","title":"Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2206.07238","title":"Location-based Twitter Filtering for the Creation of Low-Resource Language Datasets in Indonesian Local Languages","created":"2022-06-15","cited_by_count":1,"area":null},{"id":"2503.06534","title":"SafeSpeech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversations","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2306.06598","title":"RoBERTweet: A BERT Language Model for Romanian Tweets","created":"2023-06-11","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":"2503.00417","title":"A Multi-Labeled Dataset for Indonesian Discourse: Examining Toxicity, Polarization, and Demographics Information","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2503.04279","title":"Dual-Class Prompt Generation: Enhancing Indonesian Gender-Based Hate Speech Detection through Data Augmentation","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2506.11467","title":"A Gamified Evaluation and Recruitment Platform for Low Resource Language Machine Translation Systems","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2605.04885","title":"A Comparative Study of PyCaret AutoML and CNN-BiLSTM for Binary Hate Speech Detection in Indonesian Twitter","created":"2026-05-06","cited_by_count":0,"area":null}],"next_cursor":null}