Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 6 of 6 for “"Hallucination detection"”.
-
Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
… the other, their reliability is compromised by hallucinations and out-of-distribution errors, while their scale imposes severe efficiency and deployment barriers. This thesis develops a unifying spectral framework, grounded in Random Matrix Theory (RMT), to address both reliability and …
-
Beyond pre-training: continual learning and hallucinations in transformer-based language models.
… of recent approaches to detecting and mitigating hallucinations in large language models (LLMs) is conducted, identifying (1) a gap in how different LLM layers are used during detection and (2) the need for fine-grained detection between hallucinated and non-hallucinated responses to the same …
-
Generative modelling under epistemic uncertainty
… thereby providing a robust mechanism for hallucination detection. Furthermore, we propose Epistemic Generative Adversarial Networks (GANs) and Epistemic Diffusion Models. By modeling the uncertainty of the generation process itself via second-order distributions, these architectures …
-
Computational Analysis and Network-based Modeling of Cross-Species Transmissions
… integrates reasoning, summarization, and hallucination detection using curated unanswerable queries. Through computational modeling and graph-based analysis of CSTs, it identifies potential missing links and delivers an accessible and accurate CST information framework, facilitating early …
-
Improving Abstractive Summarization and Information Consistency Assessment
… motivated by summary assessment are applied to hallucination detection in large language models. The first area examined in this thesis includes two aspects of summary generation. The first aspect is associated with the diversity issue when training a model from scratch with limited data. The …
-
AI-Serve: Empowering Service Provisioning with Conversational and Generative AI
… these models also suffer from drawbacks such as hallucination, inconsistent reliability, and the lack of well-defined metrics to evaluate their responses, which limits the safe deployment in sensitive domains such as healthcare. This dissertation contributes to advancing conversational AI in …