3 papers
cs.LG2024
Heat Death of Generative Models in Closed-Loop Learning
Matteo Marchi, Stefano Soatto, Pratik Chaudhari +1
Improvement and adoption of generative machine learning models is rapidly accelerating, as exemplified by the popularity of LLMs (Large Language Models) for text, and diffusion mod…
cs.CL2024
Cycles of Thought: Measuring LLM Confidence through Stable Explanations
Evan Becker, Stefano Soatto
In many high-risk machine learning applications it is essential for a model to indicate when it is uncertain about a prediction. While large language models (LLMs) can reach and ev…
cs.AI2024
Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI
Tian Yu Liu, Stefano Soatto, Matteo Marchi +2
We tackle the question of whether Large Language Models (LLMs), viewed as dynamical systems with state evolving in the embedding space of symbolic tokens, are observable. That is,…