Doppelgänger's Watch: A Split Objective Approach to Large Language Models

Abstract: In this paper, we investigate the problem of "generation supervision" in LLMs, and present a novel bicameral architecture to separate supervision signals from their core capability, helpfulness. Doppelg\"anger, a new module parallel to the underlying LLM, supervises the generation of each token, and learns to concurrently predict the supervision score(s) of the sequences up to and including each token. In this work, we present the theoretical findings, and leave the report on experimental results to a forthcoming publication.