We propose Multiple Experts Fine-tuning Framework to build a financial large
language model (LLM), DISC-FinLLM. Our methodology improves general LLMs by
endowing them with multi-turn question answering abilities, domain text
processing capabilities, mathematical computation skills, and
retrieval-enhanced generation capabilities. We build a financial
instruction-tuning dataset named DISC-FIN-SFT, including instruction samples of
four categories (consulting, NLP tasks, computing and retrieval-augmented
generation). Evaluations conducted on multiple benchmarks demonstrate that our
model performs better than baseline models in various financial scenarios.
Further resources can be found at this https URL

我们提出了一种多专家微调框架来构建金融领域的大型语言模型（LLM），DISC-FinLLM。我们的方法通过赋予通用 LLMs 多轮问答能力、领域文本处理能力、数学计算技巧和检索增强生成能力来改进通用 LLMs。我们构建了一个金融指令微调数据集，名为 DISC-FIN-SFT，其中包括四个类别（咨询、自然语言处理任务、计算和检索增强生成）的指令样本。在多个基准测试中进行的评估表明，我们的模型在各种金融场景中比基准模型表现更好。更多资源可以在此 https 链接中找到。