Mitigating LLM Hallucination in the Banking Domain
Name
sert-dsert-meng-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
413.47 KB
Format
Adobe PDF
Checksum (MD5)
1bb35b9a6734e6d2f9f824270c661e3a
Author(s)
Sert, Deniz Bilge
Advisor(s)
Gupta, Amar
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
Large Language Models (LLMs) offer significant potential in the banking sector, particularly for applications such as fraud detection, credit approval, and enhancing customer experience. However, their tendency to "hallucinate"—generating plausible but inaccurate information—poses a critical challenge. This thesis examines existing strategies for mitigating LLM hallucinations and proposes a novel approach to reduce hallucinations in the context of predicting customer churn using LLMs.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
