Reasoning with financial regulatory texts via Large Language Models

Bledar Fazlija, Meriton Ibraimi, Aynaz Forouzandeh and Arber Fazlija

Journal of Behavioral and Experimental Finance, 2025, vol. 47, issue C

Abstract: Interpreting complex financial regulatory texts, such as the Basel III Accords, can be challenging even for human experts. In this paper, we explore the potential of Large Language Models (LLMs) to perform such tasks. Specifically, we evaluate reasoning strategies, namely Chain-of-Thought (CoT) and Tree-of-Thought (ToT), in their ability to assign accurate risk weights to test cases based on the Basel III Standardized Approach (SA) for Credit Risk. Moreover, we propose and test a guided learning-based few-shot variant of CoT and ToT using human expert input. By evaluating 6,501 test cases, comprised of diverse exposure scenarios, our results demonstrate that few-shot prompting with CoT as well as ToT significantly enhances the LLMs’ accuracy in inferring risk weights. For one-shot CoT, we observe gains of almost 13 percentage points in accuracy with GPT-4o, whereas Claude 3 Sonnet shows gains of more than 10 percentage points. Albeit smaller in magnitude, one-shot ToT improvements are around 9 percentage points.

Keywords: Financial regulation; Compliance; Basel III; Large Language Models; Machine learning; Code generation; Generative AI; Artificial intelligence; Responsible AI; Chain-of-Thought; Tree-of-Thought (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S2214635025000486

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:beexfi:v:47:y:2025:i:c:s2214635025000486

DOI: 10.1016/j.jbef.2025.101067

Access Statistics for this article

Journal of Behavioral and Experimental Finance is currently edited by Michael Dowling and Jürgen Huber

More articles in Journal of Behavioral and Experimental Finance from Elsevier
Bibliographic data for series maintained by Catherine Liu ().