RAG 能在多大程度上帮助大语言模型的推理？
How Much Can RAG Help the Reasoning of LLM?
AI总结：
本文研究检索增强生成（RAG）对大语言模型推理能力的帮助程度，发现其辅助有限且难以支持深层推理，并提出 DPrompt tuning 方法以在有限 transformer 层内有效解决文档预处理问题并提升性能。
摘要：
检索增强生成（RAG）在现代大语言模型（LLM）中因其在引入新知识和减少幻觉方面的有效性而获得了显著普及。然而，对 RAG 的深入理解仍然有限，RAG 如何帮助推理过程以及 RAG 能否帮助提升推理能力仍然是一个问题。虽然外部文档通常被视为引入领域特定信息的一种方法，但它们也包含与查询相关的中间推理结果，这表明文档可以增强大语言模型的推理能力，而这一点此前尚未被探索过。在本文中，我们深入研究了这一问题，发现虽然 RAG 可以辅助推理，但这种帮助是有限的。如果我们将推理过程概念化为一棵具有固定深度的树，那么 RAG 难以帮助大语言模型执行更深层次的推理。此外，文档中的信息需要经过预处理以过滤噪声。我们证明，这种预处理很难仅通过对大语言模型进行微调来实现，通常需要大量额外的 transformer 层才能解决该问题。为了简化该问题，我们提出了 DPrompt tuning，它能够在仅有限的 transformer 层内有效解决该问题，从而带来性能提升。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
