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

2025/05/31 by Yuelyu Ji, Ji, Yuelyu, Hang Zhang +9 · 1 citation
Business, Management and Accounting · #Business Process Modeling and Analysis #Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2506.00671

openalex publication_date 2025/05/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Data Augmentation Through Random Style Replacement
• Optimized Path Planning for Logistics Robots Using Ant Colony Algorithm under Multiple Constraints
• GraphRAG under Fire
• DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
• Scalability Optimization in Cloud-Based AI Inference Services: Strategies for Real-Time Load Balancing and Automated Scaling
• Scam Detection for Ethereum Smart Contracts: Leveraging Graph Representation Learning for Secure Blockchain
• Advances in APPFL: A Comprehensive and Extensible Federated Learning Framework
• A Neural Matrix Decomposition Recommender System Model based on the Multimodal Large Language Model
• RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts
• ComposerX: Multi-Agent Symbolic Music Composition with LLMs
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Supervising the search process produces reliable and generalizable information-seeking agents
• Assertion Detection Large Language Model In-context Learning LoRA Fine-tuning

Cited by

• Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation

Related

• MedBioLM: Optimizing Medical and Biological QA with Fine-Tuned Large Language Models and Retrieval-Augmented Generation
• MedBioRAG: Semantic Search and Retrieval-Augmented Generation with Large Language Models for Medical and Biological QA
• Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
• Optimizing Medical Question-Answering Systems: A Comparative Study of Fine-Tuned and Zero-Shot Large Language Models with RAG Framework
• BioRAG: A RAG-LLM Framework for Biological Question Reasoning