← all papers · overview

The Mosaic Memory Of Large Language Models

Abstract

As Large Language Models (LLMs) become widely adopted, understanding how they learn from, and memorize, training data becomes crucial. Memorization in LLMs is widely assumed to only occur as a result of sequences being repeated in the training data. Instead, we show that LLMs memorize by assembling information from similar sequences, a phenomena we call mosaic memory. We show major LLMs to exhibit

Related papers

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