Community Paper Reading – The Geometry of Truth: Emergent Linear Structure in LLM Representation of True/False Datasets
Registration
Registration Closed
This event is not currently taking registrations. You may contact the host or subscribe to receive updates.
About Event
This week, we’re excited to be joined by Samuel Marks, Postdoctoral Research Associate at Northwestern University, to discuss his paper, “The Geometry of Truth: Emergent Linear Structure in LLM Representation of True/False Datasets”. Samuel and his team curated high-quality datasets of true/false statements and used them to study in detail the structure of LLM representations of truth. Overall, they present evidence that language models linearly represent the truth or falsehood of factual statements and also introduce a novel technique, mass-mean probing, which generalizes better and is more causally implicated in model outputs than other probing techniques.
Link to paper: https://arxiv.org/abs/2310.06824
