Personalized LLM Response Generation with Parameterized Memory Injection
This work addresses personalized response generation for individuals in critical areas like medical, but it appears incremental as it builds on existing memory-augmented methods.
The paper tackles the problem of personalized LLM response generation by proposing a memory-injected approach using parameter-efficient fine-tuning and Bayesian optimization, achieving improved personalization without specifying concrete numerical results.
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}).