Tuning LLMs by RAG Principles: Towards LLM-native Memory
Authors:
- Jiale WeiJWJiale Wei
- Shuchi WuSWShuchi Wu
- Ruochen LiuRLRuochen Liu
- Xiang YingXYXiang Ying
- Jingbo ShangJSJingbo Shang
- Fangbo TaoFTFangbo Tao
Preprint
Abstract
Memory, additional information beyond the training of large language models (LLMs), is crucial to various real-world applications, such as personal assistant. The two mainstream solutions to incorporate memory into the generation process are long-context LLMs and retrieval-augmented generation (RAG). In this paper, we first systematically compare these two types of solutions on three renovated/new datasets and show that (1) long-context solutions, although more expensive, shall be easier to capture the big picture and better answer queries which require considering the memory as a whole; and (2) when the queries concern specific information, RAG solutions shall be more competitive especially when the keywords can be explicitly matched. Therefore, we propose a novel method RAG-Tuned-LLM which fine-tunes a relative small (e.g., 7B) LLM using the data generated following the RAG principles, so it can combine the advantages of both solutions. Extensive experiments on three datasets demonstrate that RAG-Tuned-LLM can beat long-context LLMs and RAG methods across a wide range of query types.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge2025
- Full Parameter Fine-tuning for Large Language Models with Limited Resources2024
- Parameter-efficient fine-tuning of large-scale pre-trained language modelsNature Machine Intelligence, 2023
- ♫ MuSiQue: Multihop Questions via Single-hop Question CompositionTransactions of the Association for Computational Linguistics, 2022
- Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models2022
- BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models2022
- The NarrativeQA Reading Comprehension ChallengeTransactions of the Association for Computational Linguistics, 2018