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.

 

Citation:

L. Hillebrand, A. Berger, T. Deußer, T. Dilmaghani, M. Khaled, B. Kliem, R. Loitz, M. Pielka, D. Leonhard, C. Bauckhage, and R. Sifa, “Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models,” ACM Digital Library, Aug. 2023, doi: 10.1145/3573128.3609344.

 

More Information:

Open source: https://dl.acm.org/doi/abs/10.1145/3573128.3609344