AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Yujia, Liu, Zheng, Dou, Zhicheng
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916476913451008
author Zhou, Yujia
Liu, Zheng
Dou, Zhicheng
author_facet Zhou, Yujia
Liu, Zheng
Dou, Zhicheng
contents The emergence of Large Language Models (LLMs) has significantly advanced natural language processing, but these models often generate factually incorrect information, known as "hallucination". Initial retrieval-augmented generation (RAG) methods like the "Retrieve-Read" framework was inadequate for complex reasoning tasks. Subsequent prompt-based RAG strategies and Supervised Fine-Tuning (SFT) methods improved performance but required frequent retraining and risked altering foundational LLM capabilities. To cope with these challenges, we propose Assistant-based Retrieval-Augmented Generation (AssistRAG), integrating an intelligent information assistant within LLMs. This assistant manages memory and knowledge through tool usage, action execution, memory building, and plan specification. Using a two-phase training approach, Curriculum Assistant Learning and Reinforced Preference Optimization. AssistRAG enhances information retrieval and decision-making. Experiments show AssistRAG significantly outperforms benchmarks, especially benefiting less advanced LLMs, by providing superior reasoning capabilities and accurate responses.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06805
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant
Zhou, Yujia
Liu, Zheng
Dou, Zhicheng
Computation and Language
Artificial Intelligence
Information Retrieval
The emergence of Large Language Models (LLMs) has significantly advanced natural language processing, but these models often generate factually incorrect information, known as "hallucination". Initial retrieval-augmented generation (RAG) methods like the "Retrieve-Read" framework was inadequate for complex reasoning tasks. Subsequent prompt-based RAG strategies and Supervised Fine-Tuning (SFT) methods improved performance but required frequent retraining and risked altering foundational LLM capabilities. To cope with these challenges, we propose Assistant-based Retrieval-Augmented Generation (AssistRAG), integrating an intelligent information assistant within LLMs. This assistant manages memory and knowledge through tool usage, action execution, memory building, and plan specification. Using a two-phase training approach, Curriculum Assistant Learning and Reinforced Preference Optimization. AssistRAG enhances information retrieval and decision-making. Experiments show AssistRAG significantly outperforms benchmarks, especially benefiting less advanced LLMs, by providing superior reasoning capabilities and accurate responses.
title AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistant
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2411.06805