Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering

TL;DR

This paper introduces CondMedQA, a new benchmark for conditional biomedical question answering, and proposes Condition-Gated Reasoning (CGR), a framework that improves context-aware medical reasoning by selectively activating relevant knowledge paths.

Contribution

The paper presents the first benchmark for conditional biomedical QA and a novel CGR framework that explicitly models patient-specific conditions for improved reasoning accuracy.

Findings

CGR outperforms existing models on biomedical QA benchmarks.

Explicit modeling of conditionality enhances reasoning reliability.

CGR effectively selects condition-appropriate answers.

Abstract

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.