Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models

2023/08/11 by Hillebrand, Lars, Berger, Armin, Deußer, Tobias +8 · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2308.06111

Abstract

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.

Cited by

• Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matching

Related

• Zero-Shot Text Matching for Automated Auditing using Sentence Transformers
• Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models
• FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs
• RAG-IT: Retrieval-Augmented Instruction Tuning for Automated Financial Analysis -- A Case Study for the Semiconductor Sector
• Automating Financial Statement Audits with Large Language Models