2026-09-18T19:34:34Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1629442025-10-07T04:13:41Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Gupta, Amar
Sert, Deniz Bilge
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2025-10-06T17:36:08Z
2025-10-06T17:36:08Z
2025-05
2025-06-23T14:03:33.728Z
https://hdl.handle.net/1721.1/162944
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.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Mitigating LLM Hallucination in the Banking Domain
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="63befa34-9d5d-437c-b7a3-cbfb85ec82ba">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Mitigating LLM Hallucination in the Banking Domain</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2025-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Sert, Deniz Bilge</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<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.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>