让大模型自己选最优答案，提升检索增强生成的准确性。
Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection
- 让模型在内部知识和外部检索知识生成的答案间自行选择最优解。
- 在NQ和TrivialQA数据集上，准确率显著优于基线方法。
- 适用于需要高可靠性的问答系统，尤其适合开源大模型优化。
检索增强生成（RAG）通过将外部知识融入大语言模型（LLM），有效提升了生成回答的准确性和可靠性。然而，如何高效融合外部检索知识与模型内部参数化知识仍是重大挑战。本文提出一种新型自选择RAG框架，使模型在仅使用内部知识和结合外部检索知识生成的两组答案中进行自主选择，以提升准确性。为此，我们构建了经过筛选的检索生成偏好（RGP）数据集，并采用直接偏好优化（DPO）训练模型，增强其生成与选择正确答案的能力。在两个开源LLM（Llama2-13B-Chat 和 Mistral-7B）上的实验结果表明，该方法在Natural Questions（NQ）和TrivialQA数据集上均显著优于其他基线方法。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG), which integrates external knowledge into Large Language Models (LLMs), has proven effective in enabling LLMs to produce more accurate and reliable responses. However, it remains a significant challenge how to effectively integrate external retrieved knowledge with internal parametric knowledge in LLMs. In this work, we propose a novel Self-Selection RAG framework, where the LLM is made to select from pairwise responses generated with internal parametric knowledge solely and with external retrieved knowledge together to achieve enhanced accuracy. To this end, we devise a Self-Selection-RGP method to enhance the capabilities of the LLM in both generating and selecting the correct answer, by training the LLM with Direct Preference Optimization (DPO) over a curated Retrieval Generation Preference (RGP) dataset. Experimental results with two open-source LLMs (i.e., Llama2-13B-Chat and Mistral-7B) well demonstrate the superiority of our approach over other baseline methods on Natural Questions (NQ) and TrivialQA datasets.
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。