Personalized Large Language Model Assistant with Evolving Conditional Memory

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yuan, Ruifeng, Sun, Shichao, Li, Yongqi, Wang, Zili, Cao, Ziqiang, Li, Wenjie
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916435783057408
author Yuan, Ruifeng
Sun, Shichao
Li, Yongqi
Wang, Zili
Cao, Ziqiang
Li, Wenjie
author_facet Yuan, Ruifeng
Sun, Shichao
Li, Yongqi
Wang, Zili
Cao, Ziqiang
Li, Wenjie
contents With the rapid development of large language models, AI assistants like ChatGPT have become increasingly integrated into people's works and lives but are limited in personalized services. In this paper, we present a plug-and-play framework that could facilitate personalized large language model assistants with evolving conditional memory. The personalized assistant focuses on intelligently preserving the knowledge and experience from the history dialogue with the user, which can be applied to future tailored responses that better align with the user's preferences. Generally, the assistant generates a set of records from the dialogue dialogue, stores them in a memory bank, and retrieves related memory to improve the quality of the response. For the crucial memory design, we explore different ways of constructing the memory and propose a new memorizing mechanism named conditional memory. We also investigate the retrieval and usage of memory in the generation process. We build the first benchmark to evaluate personalized assistants' ability from three aspects. The experimental results illustrate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17257
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Personalized Large Language Model Assistant with Evolving Conditional Memory
Yuan, Ruifeng
Sun, Shichao
Li, Yongqi
Wang, Zili
Cao, Ziqiang
Li, Wenjie
Computation and Language
Artificial Intelligence
With the rapid development of large language models, AI assistants like ChatGPT have become increasingly integrated into people's works and lives but are limited in personalized services. In this paper, we present a plug-and-play framework that could facilitate personalized large language model assistants with evolving conditional memory. The personalized assistant focuses on intelligently preserving the knowledge and experience from the history dialogue with the user, which can be applied to future tailored responses that better align with the user's preferences. Generally, the assistant generates a set of records from the dialogue dialogue, stores them in a memory bank, and retrieves related memory to improve the quality of the response. For the crucial memory design, we explore different ways of constructing the memory and propose a new memorizing mechanism named conditional memory. We also investigate the retrieval and usage of memory in the generation process. We build the first benchmark to evaluate personalized assistants' ability from three aspects. The experimental results illustrate the effectiveness of our method.
title Personalized Large Language Model Assistant with Evolving Conditional Memory
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2312.17257