No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks
This work addresses the need for bilingual financial NLP tools, particularly for Chinese-English applications, but it is incremental as it builds on existing multilingual and financial LLM approaches.
The authors tackled the problem of limited bilingual Chinese-English capacity in financial large language models by introducing ICE-PIXIU, which integrates a model, instruction data, and benchmarks, resulting in significant enhancements over existing models in bilingual financial analysis with a dataset of 95k entries across 30 tasks.
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.