2026-09-18T20:55:41Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1648512026-02-13T03:49:22Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Ghassemi, Marzyeh
Li, Angela
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2026-02-12T17:14:32Z
2026-02-12T17:14:32Z
2025-09
2025-09-15T14:56:32.588Z
https://hdl.handle.net/1721.1/164851
Large Language Models (LLMs) have demonstrated remarkable success in many applications; however, their reliability remains a critical concern, especially in high-stakes domains such as healthcare, finance, and law. Uncertainty Quantification (UQ) is essential for assessing LLM outputs and ensuring trust. However, existing UQ methods for LLMs face challenges: high computational costs, difficulties in handling unstructured outputs, and limited generalizability. This thesis addresses these challenges by proposing a systematic investigation into robust and efficient UQ methodologies tailored for LLMs. Specifically, this work focuses on: (1) analyzing probing methods to determine how hidden layers encode information relevant to uncertainty and accuracy, (2) developing novel UQ metrics that strongly correlate with actual model performance, and (3) designing computationally efficient pipelines to make UQ practical for real-world applications. By bridging these gaps, this research aims to establish UQ as a reliable tool for evaluating and improving the trustworthiness of LLM outputs, facilitating their safe and effective deployment in critical domains.
MNG
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Efficient Uncertainty Quantification of Large Language
Models
Thesis
application/pdf
Master
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="90203206-ee4f-46ae-aa6e-6fb55ffb6a34">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Efficient Uncertainty Quantification of Large Language
Models</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2025-09</PublicationDate>
<Authors>
<Author>
<DisplayName>Li, Angela</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) have demonstrated remarkable success in many applications; however, their reliability remains a critical concern, especially in high-stakes domains such as healthcare, finance, and law. Uncertainty Quantification (UQ) is essential for assessing LLM outputs and ensuring trust. However, existing UQ methods for LLMs face challenges: high computational costs, difficulties in handling unstructured outputs, and limited generalizability. This thesis addresses these challenges by proposing a systematic investigation into robust and efficient UQ methodologies tailored for LLMs. Specifically, this work focuses on: (1) analyzing probing methods to determine how hidden layers encode information relevant to uncertainty and accuracy, (2) developing novel UQ metrics that strongly correlate with actual model performance, and (3) designing computationally efficient pipelines to make UQ practical for real-world applications. By bridging these gaps, this research aims to establish UQ as a reliable tool for evaluating and improving the trustworthiness of LLM outputs, facilitating their safe and effective deployment in critical domains.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>