Biomedical Hypothesis Explainability with Graph-Based Context Retrieval

TL;DR

This paper presents a graph-based explainability framework for biomedical hypothesis generation that leverages retrieval-augmented language models and iterative feedback to improve explanation quality using scientific literature.

Contribution

It introduces a novel context retrieval framework combined with LLMs and a feedback loop for improved biomedical hypothesis explanation.

Findings

Effective retrieval of relevant scientific literature.

Enhanced explanation quality through iterative feedback.

Demonstrated improvements with multiple large language models.

Abstract

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.