Structure Guided Retrieval-Augmented Generation for Factual Queries

2026-04-21 · Miao Xie, Xiao Zhang, Yi Li, Chunli Lv arxiv

Retrieval-Augmented Generation (RAG) has been proposed to mitigate hallucinations in large language models (LLMs), where generated outputs may be factually incorrect. However, existing RAG approaches predominantly rely on vector similarity for retrieval, which is prone to semantic noise and fails to ensure that generated responses fully satisfy the complex conditions specified by factual queries, often leading to incorrect answers. To address this challenge, we introduce a novel research problem, named Exact Retrieval Problem (ERP). To the best of our knowledge, this is the first problem formulation that explicitly incorporates structural information into RAG for factual questions to satisfy all query conditions. For this novel problem, we propose Structure Guided Retrieval-Augmented Generation (SG-RAG), which models the retrieval process as an embedding-based subgraph matching task, and uses the retrieved topological structures to guide the LLM to generate answers that meet all specified query conditions. To facilitate evaluation of ERP, we construct and publicly release Exact Retrieval Question Answering (ERQA), a large-scale dataset comprising 120000 fact-oriented QA pairs, each involving complex conditions, spanning 20 diverse domains. The experimental results demonstrate that SG-RAG significantly outperforms strong baselines on ERQA, delivering absolute improvements from 20.68 to 50.88 points across all evaluation metrics, while maintaining reasonable computational overhead.

📄 PDF Abstract BibTeX arXiv:2604.22843

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Removal of Hallucination on Hallucination: Debate-Augmented RAG

2025-05-24 · Wentao Hu, WengYu Zhang, Yiyang Jiang, Chen Jason Zhang 외

Retrieval-Augmented Generation (RAG) enhances factual accuracy by integrating external knowledge, yet it introduces a critical issue: erroneous or biased retrieval can mislead generation, compounding hallucinations, a ph…

Hallucination RAG Retrieval Retrieval-augmented Generation

When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation

2026-08-17 · Haolin Jin, Pengyue Yang, Huaming Chen arxiv

Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trust problem: retrieved context may be useful, irrelevant, or even mislea…

EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generation

2026-01-29 · Lang Cao, Qingyu Chen, Yue Guo arxiv

Electronic Health Records (EHRs) provide rich longitudinal clinical evidence that is central to medical decision-making, motivating the use of retrieval-augmented generation (RAG) to ground large language model (LLM) pre…

CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation

2025-04-17 · Elahe Khatibi, Ziyu Wang, Amir M. Rahmani

Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG frameworks primarily rely on …

RAG Retrieval Retrieval-augmented Generation Semantic Similarity+1

ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation

2025-03-27 · Zhicheng Lee, Shulin Cao, Jinxin Liu, Jiajie Zhang 외

Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy. While recent works equip reinforcement learning (RL)-based LRMs with retrieval c…

Question Answering RAG Reinforcement Learning (RL)Retrieval+1