arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.03053cs.CLcs.LG
收藏

多语言马来西亚嵌入:利用大型语言模型进行语义表示

Multi-Lingual Malaysian Embedding: Leveraging Large Language Models for Semantic Representations

Husein Zolkepli, Aisyah Razak, Kamarul Adha, Ariff Nazhan

AI总结:

本研究微调Llama2和Mistral模型用于马来西亚语嵌入,在语义相似性和RAG任务上超越OpenAI基线,验证了微调策略的有效性。

摘要:

在这项工作中,我们对马来西亚语言模型(特别是Llama2和Mistral)在涉及负样本对和正样本对的嵌入任务上的微调进行了全面探索。我们发布了两个不同的模型,分别用于语义相似性和检索增强生成(RAG)。对于语义相似性,我们的6亿参数Llama2模型在b.cari.com.my、c.cari.com.my、马来新闻和马来西亚Twitter测试集上的所有recall@k指标上均优于OpenAI text-embedding-ada-002。在RAG模型领域,我们的方法在马来西亚语境中与OpenAI text-embedding-ada-002相比具有竞争力。值得注意的是,我们的20亿参数Llama2模型在“Melayu”关键词研究论文数据集上取得了优越的Recall@5、Recall@10,并在lom.agc.gov.my数据集上在Recall@3、Recall@5和Recall@10方面表现出色。这些发现强调了我们的微调策略的有效性,并突出了在语义相似性和RAG任务中的性能提升。所有模型已在https://huggingface.co/collections/mesolitica/malaysian-embedding-6523612bfe5881ad35f81b99发布。

英文摘要:

In this work, we present a comprehensive exploration of finetuning Malaysian language models, specifically Llama2 and Mistral, on embedding tasks involving negative and positive pairs. We release two distinct models tailored for Semantic Similarity and Retrieval-Augmented Generation (RAG). For Semantic Similarity, our 600 million parameter Llama2 model outperforms OpenAI text-embedding-ada-002 across all recall@k metrics for b.cari.com.my, c.cari.com.my, Malay news, and Malaysian Twitter test sets. In the realm of RAG models, our approach proves competitive with OpenAI text-embedding-ada-002 in the Malaysian context. Notably, our 2 billion parameter Llama2 model achieves superior Recall@5, Recall@10 for the "Melayu" keyword research papers dataset and excels in Recall@3, Recall@5, and Recall@10 for the lom.agc.gov.my dataset. These findings underscore the effectiveness of our finetuning strategy and highlight the performance gains in both Semantic Similarity and RAG tasks. All models released at https://huggingface.co/collections/mesolitica/malaysian-embedding-6523612bfe5881ad35f81b99

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑