Persianllama: Towards building first persian large language model

C Li, M Chen, J Wang, S Sitaram, X Xie - arXiv preprint arXiv:2402.10946, 2024 - arxiv.org

Large language models (LLMs) are reported to be partial to certain cultures owing to the
training data dominance from the English corpora. Since multilingual cultural data are often …

被引用次数：28 相关文章所有 2 个版本

[PDF] arxiv.org

Sabi\'a-2: A New Generation of Portuguese Large Language Models

TS Almeida, H Abonizio, R Nogueira… - arXiv preprint arXiv …, 2024 - arxiv.org

We introduce Sabi\'a-2, a family of large language models trained on Portuguese texts. The
models are evaluated on a diverse range of exams, including entry-level tests for Brazilian …

被引用次数：8 相关文章

[PDF] arxiv.org

CRAFT: Extracting and Tuning Cultural Instructions from the Wild

B Wang, G Lin, Z Liu, C Wei, NF Chen - arXiv preprint arXiv:2405.03138, 2024 - arxiv.org

Large language models (LLMs) have rapidly evolved as the foundation of various natural
language processing (NLP) applications. Despite their wide use cases, their understanding …

被引用次数：2 相关文章所有 2 个版本

[PDF] arxiv.org

CulturePark: Boosting Cross-cultural Understanding in Large Language Models

C Li, D Teney, L Yang, Q Wen, X Xie… - arXiv preprint arXiv …, 2024 - arxiv.org

Cultural bias is pervasive in many large language models (LLMs), largely due to the
deficiency of data representative of different cultures. Typically, cultural datasets and …

被引用次数：8 相关文章所有 2 个版本

[PDF] arxiv.org

Survey of Cultural Awareness in Language Models: Text and Beyond

S Pawar, J Park, J Jin, A Arora, J Myung… - arXiv preprint arXiv …, 2024 - arxiv.org

Large-scale deployment of large language models (LLMs) in various applications, such as
chatbots and virtual assistants, requires LLMs to be culturally sensitive to the user to ensure …

PersianRAG: A Retrieval-Augmented Generation System for Persian Language

H Hosseini, MS Zare, AH Mohammadi… - arXiv preprint arXiv …, 2024 - arxiv.org

Retrieval augmented generation (RAG) models, which integrate large-scale pre-trained
generative models with external retrieval mechanisms, have shown significant success in …

PerkwE_COQA: enhance Persian Conversational Question Answering by combining contextual keyword extraction with Large Language Models

P Moradbeiki, N Ghadiri - arXiv preprint arXiv:2404.05406, 2024 - arxiv.org

Smart cities need the involvement of their residents to enhance quality of life. Conversational
query-answering is an emerging approach for user engagement. There is an increasing …

高级搜索

QQ 群