Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912935020855296 |
|---|---|
| author | Sun, Liwen Yu, Xiang Tan, Ming Chen, Zhuohao Cheng, Anqi Joshi, Ashutosh Xiong, Chenyan |
| author_facet | Sun, Liwen Yu, Xiang Tan, Ming Chen, Zhuohao Cheng, Anqi Joshi, Ashutosh Xiong, Chenyan |
| contents | Clinical diagnosis is time-consuming, requiring intensive interactions between patients and medical professionals. While large language models (LLMs) could ease the pre-diagnostic workload, their limited domain knowledge hinders effective medical question generation. We introduce a Knowledge Graph-augmented LLM with active in-context learning to generate relevant and important follow-up questions, KG-Followup, serving as a critical module for the pre-diagnostic assessment. The structured medical domain knowledge graph serves as a seamless patch-up to provide professional domain expertise upon which the LLM can reason. Experiments demonstrate that KG-Followup outperforms state-of-the-art methods by 5% - 8% on relevant benchmarks in recall. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01252 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation Sun, Liwen Yu, Xiang Tan, Ming Chen, Zhuohao Cheng, Anqi Joshi, Ashutosh Xiong, Chenyan Computation and Language Artificial Intelligence Clinical diagnosis is time-consuming, requiring intensive interactions between patients and medical professionals. While large language models (LLMs) could ease the pre-diagnostic workload, their limited domain knowledge hinders effective medical question generation. We introduce a Knowledge Graph-augmented LLM with active in-context learning to generate relevant and important follow-up questions, KG-Followup, serving as a critical module for the pre-diagnostic assessment. The structured medical domain knowledge graph serves as a seamless patch-up to provide professional domain expertise upon which the LLM can reason. Experiments demonstrate that KG-Followup outperforms state-of-the-art methods by 5% - 8% on relevant benchmarks in recall. |
| title | Linking Knowledge to Care: Knowledge Graph-Augmented Medical Follow-Up Question Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.01252 |