Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph
This addresses the challenge of multi-document relationships in biomedical QA, which is critical for accurate information retrieval in healthcare and research, though it appears incremental as it builds on existing RAG approaches.
The paper tackled the problem of capturing multi-document relationships in biomedical question answering by proposing a method that constructs a local knowledge graph from retrieved documents and uses layerwise summarization to contextualize a small language model. The result was achieving comparable or superior performance over RAG baselines on several biomedical QA benchmarks.
In Question Answering (QA), Retrieval Augmented Generation (RAG) has revolutionized performance in various domains. However, how to effectively capture multi-document relationships, particularly critical for biomedical tasks, remains an open question. In this work, we propose a novel method that utilizes propositional claims to construct a local knowledge graph from retrieved documents. Summaries are then derived via layerwise summarization from the knowledge graph to contextualize a small language model to perform QA. We achieved comparable or superior performance with our method over RAG baselines on several biomedical QA benchmarks. We also evaluated each individual step of our methodology over a targeted set of metrics, demonstrating its effectiveness.