Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914377217605632 |
|---|---|
| author | Parekh, Jash Rajesh Kweon, Wonbin Chan, Joey Islamaj, Rezarta Leaman, Robert Jiang, Pengcheng Wei, Chih-Hsuan Wang, Zhizheng Lu, Zhiyong Han, Jiawei |
| author_facet | Parekh, Jash Rajesh Kweon, Wonbin Chan, Joey Islamaj, Rezarta Leaman, Robert Jiang, Pengcheng Wei, Chih-Hsuan Wang, Zhizheng Lu, Zhiyong Han, Jiawei |
| contents | Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every decision depends on patient-specific factors such as comorbidities and contraindications. Existing benchmarks do not evaluate such conditional reasoning, and retrieval-augmented or graph-based methods lack explicit mechanisms to ensure that retrieved knowledge is applicable to given context. To address this gap, we propose CondMedQA, the first benchmark for conditional biomedical QA, consisting of multi-hop questions whose answers vary with patient conditions. Furthermore, we propose Condition-Gated Reasoning (CGR), a novel framework that constructs condition-aware knowledge graphs and selectively activates or prunes reasoning paths based on query conditions. Our findings show that CGR more reliably selects condition-appropriate answers while matching or exceeding state-of-the-art performance on biomedical QA benchmarks, highlighting the importance of explicitly modeling conditionality for robust medical reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17911 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering Parekh, Jash Rajesh Kweon, Wonbin Chan, Joey Islamaj, Rezarta Leaman, Robert Jiang, Pengcheng Wei, Chih-Hsuan Wang, Zhizheng Lu, Zhiyong Han, Jiawei Computation and Language Artificial Intelligence Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every decision depends on patient-specific factors such as comorbidities and contraindications. Existing benchmarks do not evaluate such conditional reasoning, and retrieval-augmented or graph-based methods lack explicit mechanisms to ensure that retrieved knowledge is applicable to given context. To address this gap, we propose CondMedQA, the first benchmark for conditional biomedical QA, consisting of multi-hop questions whose answers vary with patient conditions. Furthermore, we propose Condition-Gated Reasoning (CGR), a novel framework that constructs condition-aware knowledge graphs and selectively activates or prunes reasoning paths based on query conditions. Our findings show that CGR more reliably selects condition-appropriate answers while matching or exceeding state-of-the-art performance on biomedical QA benchmarks, highlighting the importance of explicitly modeling conditionality for robust medical reasoning. |
| title | Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.17911 |