Mixture of Demonstrations for Textual Graph Understanding and Question Answering

Researchers propose MixDemo, a new GraphRAG framework that uses a Mixture-of-Experts mechanism to select high-quality demonstrations for improving large language model performance in domain-specific question answering. The framework includes a query-specific graph encoder to reduce noise in retrieved subgraphs and significantly outperforms existing methods across multiple textual graph benchmarks.

• →MixDemo introduces a Mixture-of-Experts mechanism for selecting informative demonstrations in GraphRAG systems.
• →The framework addresses the problem of irrelevant information in retrieved subgraphs that degrades reasoning performance.
• →A query-specific graph encoder selectively focuses on information most relevant to the query.
• →Extensive experiments show MixDemo significantly outperforms existing GraphRAG methods.
• →The research advances textual graph-based retrieval-augmented generation for domain-specific AI applications.