动态构建知识图谱，让大模型更准地回答复杂问题。
TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
- 根据任务需求实时构建领域知识图谱，避免信息碎片化。
- 在6个公开数据集和真实业务数据上超越现有方法，尤其擅长长文本问答。
- 结合提示路由与强化学习，自动提取精准、无冗余的知识节点。
检索增强生成（RAG）通过引入外部知识提升大语言模型表现，但受限于输入上下文窗口，知识常被切分为小段，导致信息丢失，引发回答幻觉和推理链断裂。此外，传统RAG依赖非结构化知识，易引入无关信息，影响推理准确性。为此，我们提出TAdaRAG，一种基于外部源实时构建任务自适应知识图谱的新型RAG框架。具体而言，设计意图驱动的路由机制，将查询映射至特定领域的知识抽取模板；通过监督微调与基于强化学习的隐式抽取机制，确保知识整合简洁、连贯且无重复。在三个主干模型上，对六个公开基准及一个真实业务基准（NowNewsQA）的评估表明，TAdaRAG在多领域与长文本任务中均优于现有方法，展现出强大的泛化能力与实际应用价值。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which leads to information loss, resulting in response hallucinations and broken reasoning chains. Moreover, traditional RAG retrieves unstructured knowledge, introducing irrelevant details that hinder accurate reasoning. To address these issues, we propose TAdaRAG, a novel RAG framework for on-the-fly task-adaptive knowledge graph construction from external sources. Specifically, we design an intent-driven routing mechanism to a domain-specific extraction template, followed by supervised fine-tuning and a reinforcement learning-based implicit extraction mechanism, ensuring concise, coherent, and non-redundant knowledge integration. Evaluations on six public benchmarks and a real-world business benchmark (NowNewsQA) across three backbone models demonstrate that TAdaRAG outperforms existing methods across diverse domains and long-text tasks, highlighting its strong generalization and practical effectiveness.
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。