← Search

Rylee Thompson

2 accepted papers

2025

InnerThoughts: Disentangling Representations and Predictions in Large Language Models

AISTATS 2025poster

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying representations of the problem within its hidden states. Ultim…

Cited by 0SourceScholar
2022

On Evaluation Metrics for Graph Generative Models

ICLR 2022poster

In image generation, generative models can be evaluated naturally by visually inspecting model outputs. However, this is not always the case for graph generative models (GGMs), making their evaluation challenging. Currently, the standard process for evaluating GGMs suffers from three critical limita…