Mixture of Demonstrations for Textual Graph Understanding and Question Answering
This work addresses a specific bottleneck in GraphRAG for domain-specific question answering, offering an incremental improvement over existing approaches.
The paper tackles the problem of irrelevant information in retrieved subgraphs degrading reasoning performance in textual graph-based retrieval-augmented generation (GraphRAG) for domain-specific question answering, proposing MixDemo with a Mixture-of-Experts mechanism and query-specific graph encoder, which significantly outperforms existing methods in experiments across multiple benchmarks.
Textual graph-based retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm for enhancing large language models (LLMs) in domain-specific question answering. While existing approaches primarily focus on zero-shot GraphRAG, selecting high-quality demonstrations is crucial for improving reasoning and answer accuracy. Furthermore, recent studies have shown that retrieved subgraphs often contain irrelevant information, which can degrade reasoning performance. In this paper, we propose MixDemo, a novel GraphRAG framework enhanced with a Mixture-of-Experts (MoE) mechanism for selecting the most informative demonstrations under diverse question contexts. To further reduce noise in the retrieved subgraphs, we introduce a query-specific graph encoder that selectively attends to information most relevant to the query. Extensive experiments across multiple textual graph benchmarks show that MixDemo significantly outperforms existing methods.