3 papers
cs.LG2024
The Ungrounded Alignment Problem
Marc Pickett, Aakash Kumar Nain, Joseph Modayil +1
Modern machine learning systems have demonstrated substantial abilities with methods that either embrace or ignore human-provided knowledge, but combining benefits of both styles r…
cs.CL2024
Better RAG using Relevant Information Gain
Marc Pickett, Jeremy Hartman, Ayan Kumar Bhowmick +2
A common way to extend the memory of large language models (LLMs) is by retrieval augmented generation (RAG), which inserts text retrieved from a larger memory into an LLM's contex…
cs.CL2024
Transformer Layers as Painters
Qi Sun, Marc Pickett, Aakash Kumar Nain +1
Despite their nearly universal adoption for large language models, the internal workings of transformers are not well understood. We aim to better understand the impact of removing…