Personalized Large Language Model Assistant with Evolving Conditional Memory

2023-12-22 · Ruifeng Yuan, Shichao Sun, Yongqi Li, Zili Wang, Ziqiang Cao, Wenjie Li

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.

📄 PDF Abstract BibTeX arXiv:2312.17257

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelRetrieval

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

PersonaVLM: Long-Term Personalized Multimodal LLMs

2026-03-20 · Chang Nie, Chaoyou Fu, Yifan Zhang, Haihua Yang 외 arxiv

Multimodal Large Language Models (MLLMs) serve as daily assistants for millions. However, their ability to generate responses aligned with individual preferences remains limited. Prior approaches enable only static, sing…

From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent

2026-02-09 · Yuhang Wang, Feiming Xu, Zheng Lin, Guangyu He 외 arxiv

Although large language model (LLM)-based agents, exemplified by OpenClaw, are increasingly evolving from task-oriented systems into personalized AI assistants for solving complex real-world tasks, their practical deploy…

TAMEing Long Contexts in Personalization: Towards Training-Free and State-Aware MLLM Personalized Assistant

2025-12-25 · Rongpei Hong, Jian Lang, Ting Zhong, Yong Wang 외 arxiv

Multimodal Large Language Model (MLLM) Personalization is a critical research problem that facilitates personalized dialogues with MLLMs targeting specific entities (known as personalized concepts). However, existing met…

Learning Implicit User Profiles for Personalized Retrieval-Based Chatbot

2021-08-18 · Hongjin Qian, Zhicheng Dou, Yutao Zhu, Yueyuan Ma 외

In this paper, we explore the problem of developing personalized chatbots. A personalized chatbot is designed as a digital chatting assistant for a user. The key characteristic of a personalized chatbot is that it should…

Chatbot Retrieval

ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation

2025-09-26 · Jiho Kim, Junseong Choi, Woosog Chay, Daeun Kyung 외 arxiv

As large language models (LLMs) become increasingly integrated into daily life, there is growing demand for AI assistants that are not only reactive but also proactive and personalized. While recent advances have pushed …