← Teaching tandonr@arizona.edu

Trustworthy Machine Learning (Spring 2025)

Course Overview

Theme I

Foundations of Modern Language Models

From classical sequence models to attention, transformers, and pretrained language models.

Theme II

Scaling, Adaptation, and Alignment

Scaling laws, few-shot learning, instruction tuning, human feedback, and efficient open foundation models.

Theme III

Capabilities, Reasoning, and Knowledge Augmentation

Specialized capabilities, explicit reasoning, retrieval, search over thought processes, and domain knowledge.

Theme IV

LLM Safety: Jailbreaking, Defenses, and Red Teaming

How safety training fails, how adversarial attacks are constructed, and how defenses and evaluation methods respond.

Theme V

Privacy, Memorization, and Training-Data Leakage

Training-data extraction, memorization measurement, scalable attacks, and membership inference.