aiqbench analysis
This research introduces EvidenceNet, a structured dataset derived from full-text biomedical literature that leverages LLMs to extract high-fidelity evidence records into graph representations. By preserving study design and provenance rather than compressing data into flat triples, the system enables more robust retrieval-augmented generation and graph-based reasoning tasks in specialized medical domains. The release establishes a new benchmark for evidence-aware analysis, demonstrating that structured extraction from unstructured text significantly improves downstream AI performance in biomedical contexts.
Building evidence-based knowledge bases from full-text literature for disease-specific biomedical reasoning
arXiv:2603.28325v4 Announce Type: replace-cross Abstract: Biomedical knowledge resources often either preserve evidence as unstructured text or compress it into flat triples that omit study design, provenance, and quantitative support. Here we present EvidenceNet, a disease-specific dataset of record-level evidence collections and corresponding graph representations derived from full-text biomedical literature. EvidenceNet uses a large language model (LLM)-assisted pipeline to extract experimentally grounded findings as structured evidence records, normalize biomedical entities, score evidence quality, and connect related records through typed semantic relations. We release EvidenceNet-HCC with 7,872 evidence records and a corresponding graph with 10,328 nodes and 49,756 edges, and EvidenceNet-CRC with 6,622 records and a corresponding graph with 8,795 nodes and 39,361 edges. Technical validation shows high component fidelity, including 98.3% field-level extraction accuracy, 100.0% high-confidence entity-link accuracy, 87.5% fusion integrity, and 90.0% semantic relation-type accuracy. Downstream analyses show that the data support retrieval-augmented question answering and graph-based tasks such as future link prediction and target prioritization. These results establish EvidenceNet as a disease-specific biomedical knowledge base dataset for evidence-aware analysis and reuse.
Abstract:Biomedical knowledge resources often either preserve evidence as unstructured text or compress it into flat triples that omit study design, provenance, and quantitative support. Here we present EvidenceNet, a disease-specific dataset of record-level evidence collections and corresponding graph representations derived from full-text biomedical literature. EvidenceNet uses a large language model (LLM)-assisted pipeline to extract experimentally grounded findings as structured evidence records, normalize biomedical entities, score evidence quality, and connect related records through typed semantic relations. We release EvidenceNet-HCC with 7,872 evidence records and a corresponding graph with 10,328 nodes and 49,756 edges, and EvidenceNet-CRC with 6,622 records and a corresponding graph with 8,795 nodes and 39,361 edges. Technical validation shows high component fidelity, including 98.3% field-level extraction accuracy, 100.0% high-confidence entity-link accuracy, 87.5% fusion integrity, and 90.0% semantic relation-type accuracy. Downstream analyses show that the data support retrieval-augmented question answering and graph-based tasks such as future link prediction and target prioritization. These results establish EvidenceNet as a disease-specific biomedical knowledge base dataset for evidence-aware analysis and reuse.
Computational Engineering, Finance, and Science (cs.CE); Artificial Intelligence (cs.AI)
arXiv:2603.28325 [cs.CE]
(or arXiv:2603.28325v4 [cs.CE] for this version)
https://doi.org/10.48550/arXiv.2603.28325 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 265 words
