DeepRAG通过分层分解问题提升生物医学多跳问答准确率
DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA
- 将复杂问题拆解为子问题，结合语义层级监督优化推理路径
- 在MedHopQA上实现比基线模型更高的精确匹配与概念级准确率
- 适合需要精准医疗知识推理的研究者和临床决策系统开发者
我们提出DeepRAG，一种融合DeepSeek分层问题分解能力与RAG Gym统一检索增强生成优化的新型框架，针对具有挑战性的MedHopQA生物医学问答任务。DeepRAG系统性地将复杂查询分解为精确的子查询，并利用受UMLS本体指导的概念级奖励信号提升生物医学准确性。在MedHopQA数据集上的初步评估显示，DeepRAG显著优于基线模型，包括独立的DeepSeek和RAG Gym，无论在精确匹配（Exact Match）还是概念级准确率上均取得明显提升。
原文摘要 · Abstract (English)
We propose DeepRAG, a novel framework that integrates DeepSeek hierarchical question decomposition capabilities with RAG Gym unified retrieval-augmented generation optimization using process level supervision. Targeting the challenging MedHopQA biomedical question answering task, DeepRAG systematically decomposes complex queries into precise sub-queries and employs concept level reward signals informed by the UMLS ontology to enhance biomedical accuracy. Preliminary evaluations on the MedHopQA dataset indicate that DeepRAG significantly outperforms baseline models, including standalone DeepSeek and RAG Gym, achieving notable improvements in both Exact Match and concept level accuracy.
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。