RAG能辅助大模型推理，但深度推理能力提升有限。
How Much Can RAG Help the Reasoning of LLM?
- 将推理视为固定深度的树结构，研究RAG在其中的作用
- 文档需去噪预处理，单纯微调模型效果差
- 提出DPrompt调优，在少量层内显著提升性能
检索增强生成（RAG）因其引入新知识和减少幻觉的能力，在现代大语言模型中广受欢迎。然而，对RAG的深层理解仍有限：它如何帮助推理过程，以及能否提升推理能力，仍是未解之谜。尽管外部文档通常用于引入领域特定信息，它们也包含与查询相关的中间推理结果，这表明文档可能增强大模型的推理能力，但此前未被探索。本文深入研究此问题，发现虽然RAG可辅助推理，但帮助有限。若将推理过程视为具有固定深度的树结构，则RAG难以支持更深的推理。此外，文档中的信息需预处理以过滤噪声，而仅通过微调大模型难以实现，通常需要大量额外的Transformer层来解决。为简化问题，我们提出DPrompt调优，仅用少量Transformer层即可有效解决该问题，从而提升性能。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) has gained significant popularity in modern Large Language Models (LLMs) due to its effectiveness in introducing new knowledge and reducing hallucinations. However, the deep understanding of RAG remains limited, how does RAG help the reasoning process and can RAG help improve the reasoning capability remains question. While external documents are typically considered as a method to incorporate domain-specific information, they also contain intermediate reasoning results related to the query, this suggests that documents could enhance the reasoning capability of LLMs, which has not been previously explored. In this paper, we investigate this issue in depth and find that while RAG can assist with reasoning, the help is limited. If we conceptualize the reasoning process as a tree with fixed depth, then RAG struggles to assist LLMs in performing deeper reasoning. Additionally, the information in the documents requires preprocessing to filter out noise. We demonstrate that this preprocessing is difficult to achieve simply fine-tuning of the LLM, it often necessitates numerous additional transformer layers to solve the problem. To simplify the problem, we propose DPrompt tuning, which effectively resolves the issue within just limited transformer layers, leading to improved performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。