用文字说明检索与推理的逻辑连接，提升大模型问答准确率。
Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
- 通过文字注释显式建立查询与检索内容的逻辑关联
- 在复杂问答任务上达到当前最优性能
- 适合需要精准推理和可解释性的场景
传统检索增强生成（RAG）将原始检索文本直接注入大语言模型（LLM）上下文，常导致信息整合不佳。本文提出通过文字注释（Verbal Annotations）作为桥梁，明确阐述搜索查询与检索内容间的逻辑联系。实证研究发现，该方法显著提升了LLM生成准确、上下文相关的回答能力。基于此，提出Verbal-R3——一种新型代理式RAG框架，包含生成器与文字重排器。生成器进行迭代检索与推理，文字重排器返回相关性评分与文字注释，指导生成器推理过程。通过相关性引导的测试时扩展，有效分配计算资源以实现高效轨迹拓展。Verbal-R3在复杂问答基准上达到领先水平，验证了该框架的有效性。
原文摘要 · Abstract (English)
The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integration of retrieved information. This paper proposes to bridge retrieval results and the LLM's reasoning ability through Verbal Annotations, analytic narratives that explicitly articulate the logical connection between a search query and retrieved contexts. Our empirical investigation reveals the potential of Verbal Annotations to substantially enhance the LLM's ability to generate accurate, contextually-grounded responses. Motivated by this finding, we introduce Verbal-R3, a novel agentic RAG framework that consists of a Generator and a Verbal Reranker. The Generator performs iterative retrieval and reasoning, while the Verbal Reranker returns relevance scores and Verbal Annotations to guide the reasoning and answering process of the Generator. The inference process of Verbal-R3 is further refined through relevance-guided test-time scaling, which efficiently allocates test-time compute for effective trajectory expansion. Verbal-R3 achieves state-of-the-art performance on complex Question Answering benchmarks, validating the effectiveness of the proposed framework.
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。