用图检索提升生物医学假说解释力，让AI推理更贴近真实科研。
Biomedical Hypothesis Explainability with Graph-Based Context Retrieval
- 基于语义图的上下文检索，模拟真实科研中的信息约束。
- 结合大模型生成与反馈循环，自动修正假说解释中的错误路径。
- 适合需要可解释性生物医学研究的科研人员和AI医疗开发者。
我们提出一种用于生物医学假说生成系统的可解释性方法，基于新颖的假说生成上下文检索框架（Hypothesis Generation Context Retriever）。该方法结合语义图检索与数据受限训练，模拟真实发现过程中的约束条件。通过检索增强生成与大语言模型（LLMs）集成，系统能够利用已发表科学文献为假说提供上下文证据。我们还提出一种新型反馈循环机制，迭代识别并修正大模型生成解释中的缺陷，优化证据路径与支持上下文。在多个大型语言模型上验证了该方法性能，并通过专家标注评估与大规模自动化分析双重方式评价解释质量与上下文检索效果。代码已开源：https://github.com/IlyaTyagin/HGCR。
原文摘要 · Abstract (English)
We introduce an explainability method for biomedical hypothesis generation systems, built on top of the novel Hypothesis Generation Context Retriever framework. Our approach combines semantic graph-based retrieval and relevant data-restrictive training to simulate real-world discovery constraints. Integrated with large language models (LLMs) via retrieval-augmented generation, the system explains hypotheses with contextual evidence using published scientific literature. We also propose a novel feedback loop approach, which iteratively identifies and corrects flawed parts of LLM-generated explanations, refining both the evidence paths and supporting context. We demonstrate the performance of our method with multiple large language models and evaluate the explanation and context retrieval quality through both expert-curated assessment and large-scale automated analysis. Our code is available at: https://github.com/IlyaTyagin/HGCR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。