CC BY 4.0Hillebrand, Lars PatrickLars PatrickHillebrandBerger, ArminArminBergerDeußer, TobiasTobiasDeußerDilmaghani, TimTimDilmaghaniKhaled, MohamedMohamedKhaledKliem, B.B.KliemLoitz, RüdigerRüdigerLoitzPielka, MarenMarenPielkaLeonhard, DavidDavidLeonhardBauckhage, ChristianChristianBauckhageSifa, RafetRafetSifa2024-01-302024-01-302023-08-22https://publica.fraunhofer.de/handle/publica/459475https://doi.org/10.24406/publica-251810.1145/3573128.360934410.24406/publica-25182-s2.0-85173560745Auditing 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.enLarge Language ModelsRecommender SystemText Matchingconference paper