GainRAG：通过增益信号合成实现检索增强生成中的偏好对齐
GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis
AI总结：
GainRAG通过定义“增益”指标并训练中间件对齐检索器与LLM的偏好，解决RAG中的偏好差距问题，在6个数据集上验证了有效性。
摘要：
检索增强生成（RAG）框架引入检索模块，将检索到的信息动态注入大语言模型（LLM）的输入上下文中，并在各种NLP任务中取得了显著成功。然而，目前的研究指出，在RAG框架中，检索器和LLM之间存在偏好差距，这限制了系统性能的进一步提升。一些高度相关的段落可能因包含复杂或矛盾的信息而干扰LLM的推理；而一些间接相关甚至不准确的内容可能通过提供提示性信息或逻辑线索，帮助LLM生成更准确的答案。为了解决这一问题，我们提出了GainRAG，一种新颖的方法，通过定义一个新的指标“增益”（gain），来衡量输入段落对正确输出的贡献程度，从而对齐检索器和LLM的偏好。具体而言，我们提出了一种估计这些增益信号的方法，并训练一个中间件，仅使用有限的数据即可对齐检索器和LLM的偏好。此外，我们引入了一种伪段落策略来缓解性能退化。在6个数据集上的实验结果验证了GainRAG的有效性。
英文摘要：
The Retrieval-Augmented Generation (RAG) framework introduces a retrieval module to dynamically inject retrieved information into the input context of large language models (LLMs), and has demonstrated significant success in various NLP tasks. However, the current study points out that there is a preference gap between retrievers and LLMs in the RAG framework, which limit the further improvement of system performance. Some highly relevant passages may interfere with LLM reasoning because they contain complex or contradictory information; while some indirectly related or even inaccurate content may help LLM generate more accurate answers by providing suggestive information or logical clues. To solve this, we propose GainRAG, a novel approach that aligns the retriever's and LLM's preferences by defining a new metric, "gain", which measure how well an input passage contributes to correct outputs. Specifically, we propose a method to estimate these gain signals and train a middleware that aligns the preferences of the retriever and the LLM using only limited data. In addition, we introduce a pseudo-passage strategy to mitigate degradation. The experimental results on 6 datasets verify the effectiveness of GainRAG.
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。
