On the Transformations across Reward Model, Parameter Update, and In-Context Prompt
This provides a holistic roadmap for researchers working on LLM adaptation, though it is incremental in unifying existing tools rather than introducing new methods.
The paper tackles the problem of adapting pre-trained large language models for practical applications by demonstrating the interchangeability of parameter updating, reward modeling, and in-context prompting, establishing a triangular framework with six transformation directions that unify existing studies and suggest future research.
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.