Graph-Enhanced Retrieval-Augmented Generation for Postoperative Patient Question Answering: A Comparative Evaluation of Knowledge Graph, Retrieval-Augmented Generation, and Hybrid GraphRAG Approaches
GraphRAG is a multi-component pipeline that also includes query expansion, a second retrieval stage, evidence fusion, and a monotonic RAG fallback, and is therefore evaluated as a complete hybrid system rather than as graph retrieval in isolation, which reflects the complete hybrid system rather than graph augmentation alone.
Abstract
Background: Reliable access to postoperative guidance between clinic visits remains inconsistent, and the usefulness of large language models depends on how clinical knowledge is structured and retrieved. Knowledge graph-only (KG-only), vector retrieval-augmented generation (RAG-only), and hybrid graph-retrieval (GraphRAG) architectures have not been directly compared under controlled conditions for postoperative care. Objective: It was to compare these three pipelines on a curated postoperative question-answering benchmark using automated grounding metrics and blinded clinician review. Methods: A benchmark of 250 expert-authored questions (200 in-scope, 20 emergency-intent, 30 out-of-scope) was evaluated on an identical knowledge corpus using Gemini 2.5 Flash for generation and Gemini Embedding-001 for retrieval. Three blinded clinicians rated all 750 outputs; the primary outcome was majority-consensus accuracy across all 250 questions. GraphRAG is a multi-component pipeline that also includes query expansion, a second retrieval stage, evidence fusion, and a monotonic RAG fallback, and is therefore evaluated as a complete hybrid system rather than as graph retrieval in isolation. Results: Overall accuracy was 96.8% (95% CI: 93.8–98.4) for GraphRAG, 94.8% (95% CI: 91.3–96.9) for RAG-only, and 56.0% (95% CI: 49.8–62.0) for KG-only. Both retrieval-augmented systems outperformed KG-only (adjusted p < 0.001). The GraphRAG versus RAG-only difference was 2.0 percentage points, arose from five discordant question pairs and did not reach the Bonferroni-adjusted threshold (exact McNemar p = 0.062; adjusted p = 0.188). The monotonic RAG fallback determined 44.8% of GraphRAG outputs (112 of 250 queries). GraphRAG showed higher context recall (0.851 versus 0.796; adjusted p < 0.001), whereas RAG-only showed higher context precision. Estimated hallucination risk, derived from an LLM-as-a-judge procedure using Gemini 2.5 Flash rather than independent clinical adjudication, was 0.108, 0.132, and 0.436, respectively; the GraphRAG versus RAG-only difference was not significant (adjusted p = 0.771). Inter-rater agreement was high (Fleiss’ kappa = 0.854). Conclusions: Retrieval augmentation, rather than the choice of retrieval architecture, accounted for most of the difference observed. The incremental advantage of GraphRAG over a well-implemented RAG-only system was small, was not statistically significant after correction and reflects the complete hybrid system rather than graph augmentation alone. Emergency-intent accuracy was 75.0% for both retrieval-augmented systems; the architecture is therefore suited to supervised clinical workflows with clinician review, not autonomous patient-facing triage. Prospective validation on authentic patient messages and formal component ablations are required.
By transforming aggregate robustness measurement into typed diagnostic attribution, MissDiag provides a more interpretable basis for comparing, diagnosing, and stress-testing KGQA and KG-RAG systems under incomplete knowledge.
This work evaluates a confidence-adaptive graph-enhanced retrieval layer for metallurgical RAG in a controlled synthetic benchmark with explicitly specified generation and evaluation rules and shows how the retrieval rule behaves under controlled conditions.
Viktor A. Vedeneev, V. Kondratiev, A. Nazarychev et al.· International Conference on...· 0 citations
RA-QGQA is presented, which recasts triple verification as a question-driven, corpus-grounded task, and demonstrates RA-QGQA as an interactive web system in which users import a KG and its source corpus, verify all triples in a single pass, and inspect the passages that justify its verdict.
Si-Yang Liu, Hong Duc Nguyen, Yun-Miao Li et al.· Proceedings of the 2026 ACM...· 0 citations
Retrieval-Augmented Generation (RAG) with local Large Language Models (LLMs) offers a reliable and secure way to retrieve medical information. However, when querying specific data in a different language (English) with external data like Indonesian pharmaceutical corpus, it introduces problems. This study evaluates an...
Alin Lorensia, Darren Vincent, Daniel Regis Febrianto et al.· International Conferences on...· 0 citations
MERGE-Med is a hybrid multi-expert architecture that consists of a mixture-of-experts (MoE) layer with three domain-specialized LLaMA-3 8B models for diagnostic reasoning, treatment protocol generation, and patient-friendly communication and a contrastive fine-tuning framework validated by an ensembled DeBERTa-v3-large...
D. Tejaswi, P. R. Reddy, K. Shailaja et al.· Conference Proceedings in Sc...· 0 citations
Few-shot prompting heavily improves query generation quality and enables effective use of smaller models, supporting the practical deployment of locally hosted LLMs for knowledge graph question answering.
Suteera Seeha, Adem Abdelmoula, M. Boeker et al.· Studies in Health Technology...· 0 citations
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.