pith. sign in

arxiv: 2406.16377 · v1 · pith:JSK6EKHOnew · submitted 2024-06-24 · 💻 cs.CL · cs.AI

On the Transformations across Reward Model, Parameter Update, and In-Context Prompt

classification 💻 cs.CL cs.AI
keywords adaptationapplicationsdirectionsin-contextinterchangeabilityllmsparameterresearch
0
0 comments X
read the original abstract

Despite the general capabilities of pre-trained large language models (LLMs), they still need further adaptation to better serve practical applications. In this paper, we demonstrate the interchangeability of three popular and distinct adaptation tools: parameter updating, reward modeling, and in-context prompting. This interchangeability establishes a triangular framework with six transformation directions, each of which facilitates a variety of applications. Our work offers a holistic view that unifies numerous existing studies and suggests potential research directions. We envision our work as a useful roadmap for future research on LLMs.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.