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 7 of 7 for “"Language Model Alignment"”.
-
Methods for Language Model Alignment: Inference-Time Sampling and Preference Fine-Tuning
As large language models (LLMs) transition from research prototypes to widely deployed systems, aligning their outputs with human preferences and objectives has become a central challenge. While pretrained LLMs generate fluent text, they often fail to follow instructions, meet users’ objectives, or …
-
Topics in Statistical Machine Learning: Multitask Learning, Uncertainty Quantification, and Language Model Alignment
… learning, uncertainty quantification, andlanguage model alignment. In the first chapter, we investigate the challenges and opportunities in learning from large, heterogeneousdatasets, where data is collected from multiple sources with sparse heterogeneity, meaning that the …
-
PREFERENCE LEARNING AT THE INTERFACE OF AI AND OPERATIONS
… develops a novel, tractable Mallows-type ranking model that enables preferences to be learned from ranked choices and supports the design of efficient feedback systems. Moving in the opposite direction, the second study brings choice modeling ideas from operations research to AI alignment. It …
-
Aligning Language Models Using Multi-Objective Deep Reinforcement Learning
Large Language Models (LLMs) have been a significant landmark of Artificial Intelligence (AI) advancement. Aligning LLMs to be helpful and harmless is a booming trend in Natural Language Processing (NLP). One of the dominant alignment techniques is reinforcement learning from human feedback (RLHF). …
-
Trustworthy Autonomy Through Robust Control and Alignment
… reliable control through formal guarantees and alignment against adversarial manipulation. The first part of the dissertation focuses on provably stable, robust, and safe control for nonlinear systems using learning based methods. We introduce the first general framework for synthesizing neural …
-
Optimization methods for reinforcement learning: theory and applications
… in both simulated robotic tasks and a large language model alignment task, highlighting the effectiveness of our mirror descent-based approach for preference learning.
-
Generative AI for Hardening Security: From Training Data Augmentation, Language Alignment, to Code Vulnerability Demonstration
… under evolving threat landscapes. Foundation model customization pipelines are vulnerable to data poisoning that induces harmful behavioral outputs. Vulnerability detection tools identify risks in software dependencies but provide no mechanism for determining whether reported vulnerabilities …