Personalized LLM Response Generation with Parameterized Memory Injection

TL;DR

This paper introduces MiLP, a novel personalized response generation method for LLMs that uses parameter-efficient fine-tuning and Bayesian optimization to incorporate fine-grained user-specific knowledge.

Contribution

The paper proposes MiLP, a new approach combining PEFT and Bayesian optimization for fine-grained personalization in LLM response generation.

Findings

MiLP improves personalization accuracy over baseline methods.

The approach effectively incorporates user-specific knowledge.

MiLP demonstrates potential in critical domains like medical applications.

Abstract

Large Language Models (LLMs) have exhibited remarkable proficiency in comprehending and generating natural language. On the other hand, personalized LLM response generation holds the potential to offer substantial benefits for individuals in critical areas such as medical. Existing research has explored memory-augmented methods to prompt the LLM with pre-stored user-specific knowledge for personalized response generation in terms of new queries. We contend that such paradigm is unable to perceive fine-granularity information. In this study, we propose a novel \textbf{M}emory-\textbf{i}njected approach using parameter-efficient fine-tuning (PEFT) and along with a Bayesian Optimisation searching strategy to achieve \textbf{L}LM \textbf{P}ersonalization(\textbf{MiLP}).