← all papers · overview

Summing Up The Facts: Additive Mechanisms Behind Factual Recall In Llms

Abstract

How do transformer-based large language models (LLMs) store and retrieve knowledge? We focus on the most basic form of this task -- factual recall, where the model is tasked with explicitly surfacing stored facts in prompts of form `Fact: The Colosseum is in the country of'. We find that the mechanistic story behind factual recall is more complex than previously thought. It comprises several disti

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).