Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909561260081152 |
|---|---|
| author | Guan, Lingxiao Huang, Yuanhao Liu, Jie |
| author_facet | Guan, Lingxiao Huang, Yuanhao Liu, Jie |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01309 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph Guan, Lingxiao Huang, Yuanhao Liu, Jie Computation and Language Artificial Intelligence Information Retrieval 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. |
| title | Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2504.01309 |