Auditing financial documents is a very tedious and time-consuming process. As of today, it can already be simplified by employing AI-based solutions to recommend relevant text passages from a report for each legal requirement of rigorous accounting standards. However, these methods need to be fine-tuned regularly, and they require abundant annotated data, which is often lacking in industrial environments. Hence, we present ZeroShotALI, a novel recommender system that leverages a state-of-the-art large language model (LLM) in conjunction with a domain-specifically optimized transformer-based text-matching solution. We find that a two-step approach of first retrieving a number of best matching document sections per legal requirement with a custom BERT-based model and second filtering these selections using an LLM yields significant performance improvements over existing approaches.

翻译：审计财务文档是一个非常繁琐且耗时的过程。如今，通过采用基于人工智能的解决方案，为严格会计准则的每个法律要求推荐报告中的相关文本段落，已经可以简化这一过程。然而，这些方法需要定期微调，并且需要大量的人工标注数据，这在工业环境中往往难以获得。因此，我们提出了ZeroShotALI，一种新型推荐系统，它结合了先进的大型语言模型（LLM）与经过领域特定优化的基于 transformer 的文本匹配解决方案。我们发现，采用两步法：首先使用基于BERT的自定义模型为每个法律要求检索多个最佳匹配的文档章节，然后使用LLM对这些选择进行筛选，相比现有方法取得了显著的性能提升。