arXiv 2403.062492024-08-16cs.CEcs.CL

没有一种语言是孤岛：统一金融大语言模型、指令数据与基准中的中英文

No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks

Yunnan University（云南大学）；The University of Manchester（曼彻斯特大学）；Wuhan University（武汉大学）；University of Florida（佛罗里达大学）；The Chinese University of Hong Kong（香港中文大学）；The Fin AI

Gang Hu, Ke Qin, Chenhan Yuan, Min Peng, Alejandro Lopez-Lira, Benyou Wang, Sophia Ananiadou, Jimin Huang, Qianqian Xie

备注：: 19 pages, 3 figures, 12 tables, including Appendix

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有金融大语言模型多局限于单一语言的问题，研究提出融合ICE-INTENT模型与ICE-FLARE基准的双语金融分析框架ICE-PIXIU，整合多类双语任务与数据，实验验证其能显著提升双语金融NLP的准确性与效能。

摘要：

尽管大语言模型（LLMs）的发展显著推动了金融分析，但其应用大多局限于单一语言领域，中英双语能力的潜力尚未得到挖掘。为填补这一空白，我们提出ICE-PIXIU，它无缝融合了ICE-INTENT模型与ICE-FLARE基准，用于双语金融分析。ICE-PIXIU的独特之处在于整合了一系列中文任务，以及翻译版和原版英文数据集，丰富了双语金融建模的广度与深度。它提供对多种模型变体的无限制访问、大量跨语言与多模态指令数据汇编，以及带有专家标注的评估基准，涵盖10项NLP任务、20项双语专属任务，数据集总量达9.5万。我们的全面评估凸显了纳入这些双语数据集的优势，尤其是在翻译任务和原版英文数据利用方面，提升了金融场景下的语言灵活性与分析敏锐度。值得注意的是，ICE-INTENT在双语环境中相较传统LLMs和现有金融LLMs表现出显著提升，凸显了高质量双语数据对金融NLP准确性与效能的深远影响。

英文摘要：

While the progression of Large Language Models (LLMs) has notably propelled financial analysis, their application has largely been confined to singular language realms, leaving untapped the potential of bilingual Chinese-English capacity. To bridge this chasm, we introduce ICE-PIXIU, seamlessly amalgamating the ICE-INTENT model and ICE-FLARE benchmark for bilingual financial analysis. ICE-PIXIU uniquely integrates a spectrum of Chinese tasks, alongside translated and original English datasets, enriching the breadth and depth of bilingual financial modeling. It provides unrestricted access to diverse model variants, a substantial compilation of diverse cross-lingual and multi-modal instruction data, and an evaluation benchmark with expert annotations, comprising 10 NLP tasks, 20 bilingual specific tasks, totaling 95k datasets. Our thorough evaluation emphasizes the advantages of incorporating these bilingual datasets, especially in translation tasks and utilizing original English data, enhancing both linguistic flexibility and analytical acuity in financial contexts. Notably, ICE-INTENT distinguishes itself by showcasing significant enhancements over conventional LLMs and existing financial LLMs in bilingual milieus, underscoring the profound impact of robust bilingual data on the accuracy and efficacy of financial NLP.

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。