Personalized LLM Response Generation with Parameterized Memory Injection

Authors

• Kai Zhang
• Yejin Kim
• Xiaozhong Liu

Language

English

Publication Date

4-4-2024

Journal

arXiv

DOI

10.48550/arXiv.2404.03565

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}).

Published Open-Access

yes

Recommended Citation

Kai Zhang, Yejin Kim, and Xiaozhong Liu, "Personalized LLM Response Generation with Parameterized Memory Injection" (2024). Faculty, Staff and Student Publications. 972.
https://digitalcommons.library.tmc.edu/uthshis_docs/972