DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA
This addresses the problem of complex biomedical QA for researchers and clinicians, though it appears incremental as it combines existing components.
The authors tackled biomedical multi-hop question answering by proposing DeepRAG, which integrates hierarchical reasoning and process supervision; preliminary results on MedHopQA show it significantly outperforms baselines in Exact Match and concept-level accuracy.
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.