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 “"Preference Optimization"”.
-
Steerable Alignment with Conditional Multiobjective Preference Optimization
… that these systems are aligned with human preferences. Current state of the art strategies for alignment such as Reinforcement Learning from Human Feedback (RLHF) have provided useful paradigms for finetuning LLMs to produce outputs that are more consistent with human preferences. These …
-
Personalized and adaptive therapeutic music generation from biosignals using knowledge-guided multimodal large language models
… evidence-grounded reasoning, and stabilized preference alignment. At the representation layer, the dissertation develops a family of tokenizers that convert continuous biomedical and media signals into compact discrete sequences for transformer-based modeling. Harmonizer provides …
-
CONDOR: Clinical Ontology-aware Networked Data Organization and Retrieval
… and programmatically generate a high-quality preference dataset for alignment using Simple Preference Optimization (SimPO). We compare a standard vector-based Retrieval-Augmented Generation (RAG) baseline against a more advanced GraphRAG architecture that leverages a two-tiered knowledge graph …
-
Models and Application of Question Retrieval for Natural Language Processing
… distilled into model parameters through Direct Preference Optimization (DPO) and Supervised Fine-Tuning, producing standalone models with improved coherence that surpass the inference-time approach. For retrieval systems, we apply clusters to train models for consistency: the Coherence Ranking …
-
Trustworthy Federated Learning Systems: From Secure Distributed Training to Reliable Fine-tuning
… Third, it develops Behavioral Hard Probability Optimization (BHPO), a preference-based optimization method designed to improve the robustness of LLMs against prompt injection attacks. Unlike conventional preference optimization methods that rely primarily on margin-based objectives, BHPO …
-
Improving Controllability in Diffusion-Based Image Inpainting through Structured Workflows and Preference-Based Model Adaptation
… inpainting model is directly fine-tuned using preference-based optimization, together with a composite reward model and a region-aware evaluation system. Together, these approaches improve controllability at both the workflow level and the model level.