LIR$^3$AG：一种轻量级重排序推理策略框架用于检索增强生成
LIR$^3$AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
AI总结：
LIR$^3$AG通过重构检索证据为连贯推理链，使非推理模型在RAG中实现性能超越，减少计算开销并提升F1分数。
摘要：
检索增强生成（RAG）通过将检索到的外部知识整合到生成过程中，有效增强了大型语言模型（LLMs）。推理模型通过整合和推理多个文档中的多跳证据来提高LLM在多跳问答任务中的性能。然而，它们通常会引入显著的计算成本，包括增加的token消耗和推理延迟。为了更好地理解和缓解这种权衡，我们对RAG多跳问答任务中推理模型的推理策略进行了全面研究。我们的发现表明，推理模型采用结构化的策略来整合检索到的和内部知识，主要遵循两种模式：基于上下文的推理，直接依赖检索内容，以及知识协调的推理，通过内部知识解决冲突或空白。为此，我们提出了一种新的轻量级重排序推理策略框架用于RAG（LiR$^3$AG），以使非推理模型能够通过将检索到的证据重新组织成连贯的推理链来转移推理策略。LiR$^3$AG显著减少了平均98%的输出token开销和58.6%的推理时间，同时将8B非推理模型的F1性能提高6.2%至22.5%，超越了32B推理模型在RAG中的性能，为RAG系统提供了一条实用且高效的前进路径。
英文摘要：
Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require integrating and reasoning over multiple pieces of evidence across different documents to answer a complex question. However, they often introduce substantial computational costs, including increased token consumption and inference latency. To better understand and mitigate this trade-off, we conduct a comprehensive study of reasoning strategies for reasoning models in RAG multi-hop QA tasks. Our findings reveal that reasoning models adopt structured strategies to integrate retrieved and internal knowledge, primarily following two modes: Context-Grounded Reasoning, which relies directly on retrieved content, and Knowledge-Reconciled Reasoning, which resolves conflicts or gaps using internal knowledge. To this end, we propose a novel Lightweight Rerank Reasoning Strategy Framework for RAG (LiR$^3$AG) to enable non-reasoning models to transfer reasoning strategies by restructuring retrieved evidence into coherent reasoning chains. LiR$^3$AG significantly reduce the average 98% output tokens overhead and 58.6% inferencing time while improving 8B non-reasoning model's F1 performance ranging from 6.2% to 22.5% to surpass the performance of 32B reasoning model in RAG, offering a practical and efficient path forward for RAG systems.
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。
