BioPIE: A Biomedical Protocol Information Extraction Dataset for High-Reasoning-Complexity Experiment Question Answer

2026-01-08

arXiv.org

AI Summary

This work addresses the challenge that existing biomedical datasets struggle to support complex experimental question answering requiring high information density and multi-step reasoning. To bridge this gap, the authors propose BioPIE—the first fine-grained knowledge graph dataset centered on biomedical experimental procedures. BioPIE constructs structured knowledge representations by systematically extracting entities, actions, and their interrelationships from experimental protocols. This approach fills a critical void in structured knowledge for complex experimental scenarios and is integrated into a question-answering system to enable multi-hop reasoning. Experimental results demonstrate that the BioPIE-enhanced system significantly outperforms baseline models on both standard benchmarks and challenging questions, thereby substantially improving AI’s capacity to assist with experimental design and analysis.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Question Answer (QA) systems for biomedical experiments facilitate cross-disciplinary communication, and serve as a foundation for downstream tasks, e.g., laboratory automation. High Information Density (HID) and Multi-Step Reasoning (MSR) pose unique challenges for biomedical experimental QA. While extracting structured knowledge, e.g., Knowledge Graphs (KGs), can substantially benefit biomedical experimental QA. Existing biomedical datasets focus on general or coarsegrained knowledge and thus fail to support the fine-grained experimental reasoning demanded by HID and MSR. To address this gap, we introduce Biomedical Protocol Information Extraction Dataset (BioPIE), a dataset that provides procedure-centric KGs of experimental entities, actions, and relations at a scale that supports reasoning over biomedical experiments across protocols. We evaluate information extraction methods on BioPIE, and implement a QA system that leverages BioPIE, showcasing performance gains on test, HID, and MSR question sets, showing that the structured experimental knowledge in BioPIE underpins both AI-assisted and more autonomous biomedical experimentation.

Problem

• High Information Density
• Multi-Step Reasoning
• Biomedical Experiment QA
• Fine-grained Knowledge
• Protocol Understanding

Innovation

• Biomedical Protocol Information Extraction
• High Information Density
• Multi-Step Reasoning
• Knowledge Graph
• Question Answering