Back to search

The Open University

Building Trustworthy AI: Uncertainty Quantification and Failure Detection in Large Vision-Language Models

Abstract

dc:description.abstract

Despite the impressive performance of AI systems in various fields, knowing when to trust their predictions is still difficult. In this thesis, we address the critical challenges of model calibration, failure detection and uncertainty quantification to enhance the reliability and trustworthiness of AI systems. Firstly, we investigate the problem of model miscalibration, where a model's confidence in its predictions doesn't align with its actual accuracy. We propose novel metrics and calibration techniques to tackle both overconfidence and under-confidence, enhancing the reliability of model predictions. This is particularly important in safety-critical tasks where under-confidence can lead to missed detection or alerts. Secondly, we delve into the issue of failure detection. We propose new evaluation metrics, including the Excess Area Under the Optimal Risk-Coverage curve (E-AUoptRC) and the Trust Index (TI), to better assess model trustworthiness and learning ability. These metrics provide a more nuanced understanding of model performance than traditional accuracy measures. Thirdly, we explore uncertainty quantification in natural language generation (NLG) tasks, particularly in the context of large language models (LLMs). We introduce Contrastive Semantic Similarity, a Contrastive Language–Image Pre-training (CLIP) based feature extraction module, to measure semantic similarity between text pairs and estimate uncertainty. This method improves the trustworthiness of LLM-generated responses by enabling selective NLG, where unreliable generations are detected and rejected.<br></br><br></br> Throughout the thesis, we conduct extensive experiments on different modalities of language and vision, with various benchmark datasets and different model architectures, demonstrating the effectiveness of our proposed methods in improving model calibration, failure detection, and uncertainty quantification. This research contributes to the development of more reliable and safe AI systems, particularly in safety-critical domains where the consequences of model errors can be severe.

Degree

thesis:*
Name dc:type.qualificationname
phd
Level dc:type.qualificationlevel
doctoral
Grantor dc:publisher.institution
The Open University
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ao, Shuang

Rights

Language dc:language
en

Chain of custody

source
Harvested from
The Open University
Base URL
oro.open.ac.uk/cgi/oai2
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Ao, Shuang. Building Trustworthy AI: Uncertainty Quantification and Failure Detection in Large Vision-Language Models. doctoral thesis, The Open University, 2025.