DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ji, Yuelyu, Zhang, Hang, Verma, Shiven, Ji, Hui, Li, Chun, Han, Yushui, Wang, Yanshan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908388034609152
author Ji, Yuelyu
Zhang, Hang
Verma, Shiven
Ji, Hui
Li, Chun
Han, Yushui
Wang, Yanshan
author_facet Ji, Yuelyu
Zhang, Hang
Verma, Shiven
Ji, Hui
Li, Chun
Han, Yushui
Wang, Yanshan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00671
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA
Ji, Yuelyu
Zhang, Hang
Verma, Shiven
Ji, Hui
Li, Chun
Han, Yushui
Wang, Yanshan
Computation and Language
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.
title DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA
topic Computation and Language
url https://arxiv.org/abs/2506.00671