利用大型语言模型实现金融审计中的自动化合规验证
Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models
AI总结：
本文研究大型语言模型在金融审计合规验证中的表现，通过普华永道德国提供的两个定制数据集比较开源Llama-2与专有GPT模型，发现Llama-2 70B在检测不合规方面表现最佳，而GPT-4在非英语等广泛场景中表现最优。
摘要：
金融文件的审计历来是一个劳动密集型过程，如今正处于变革的前沿。人工智能驱动的解决方案已开始涉足简化这一流程，通过从财务报告中推荐相关文本段落，以符合会计准则的法律要求。然而，一个明显的局限性依然存在：这些系统通常无法验证所推荐的摘录是否确实符合具体的法律规定。因此，在本文中，我们探究了公开可用的大型语言模型（LLMs）在不同模型配置下于监管合规领域中的效率。我们特别着重比较前沿的开源LLMs（如Llama-2）与专有模型（如OpenAI的GPT系列模型）。这一比较分析利用了我们合作伙伴普华永道（PwC）德国提供的两个定制数据集。我们发现，开源的Llama-2 700亿参数模型在检测不合规或真阴性情况方面表现出色，超越了所有专有模型。然而，诸如GPT-4之类的专有模型在广泛的场景中表现最佳，尤其是在非英语语境下。
英文摘要：
The auditing of financial documents, historically a labor-intensive process, stands on the precipice of transformation. AI-driven solutions have made inroads into streamlining this process by recommending pertinent text passages from financial reports to align with the legal requirements of accounting standards. However, a glaring limitation remains: these systems commonly fall short in verifying if the recommended excerpts indeed comply with the specific legal mandates. Hence, in this paper, we probe the efficiency of publicly available Large Language Models (LLMs) in the realm of regulatory compliance across different model configurations. We place particular emphasis on comparing cutting-edge open-source LLMs, such as Llama-2, with their proprietary counterparts like OpenAI's GPT models. This comparative analysis leverages two custom datasets provided by our partner PricewaterhouseCoopers (PwC) Germany. We find that the open-source Llama-2 70 billion model demonstrates outstanding performance in detecting non-compliance or true negative occurrences, beating all their proprietary counterparts. Nevertheless, proprietary models such as GPT-4 perform the best in a broad variety of scenarios, particularly in non-English contexts.
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。
