This work improves evidence retrieval by combining semantic ranking and repository-specific identifier pattern matching and achieves recall close to that of proprietary models while reducing estimated inference cost by 330× to 1,300×, although with lower precision.
This work introduces SciDocBench, a workflow-centered benchmark targeting capability diagnosis with verifiable training-data construction for scientific-document assistants, and SciDocIR, a structured representation of scientific document objects, layout and cross-reference relations, and provenance.
Shen-Xi Wu, Yu-Hong Liu, Hao-Song Zhang et al.· 1 citation
Background: Planning multi-study analyses requires identifying cohorts with the relevant participants, phenotypes, and data modalities. This process commonly relies on prior knowledge, cohort catalogues, and manual literature searches. We developed a complementary question-driven framework that searches relevant scient...
Moritz Sturm, Lisa M. Berg, Inken Berg et al.· 0 citations
Collaborative Research Centers rely on FAIR-compliant, richly structured metadata, yet manual annotation is a major bottleneck. We implemented a search-augmented large language model (LLM) workflow within a local research data management system to pre-annotate biomedical entities, using human-in-the-loop verifica...
M. Watter, F. Engel, Aref Kalantari et al.· Bioinformatics Advances· 0 citations
The rapid expansion of biomedical literature requires automated methods for accurate and efficient information extraction. This study addresses relation classification: given a pair of annotated biomedical entities in a research article title and abstract, assigning the relation that holds between them from a pre-defin...
Jannat, Charlie Dil, Tom Arodz et al.· Frontiers in Research Metric...· 0 citations
BELXTR is presented, a novel embedding model based on the multi-vector (a.k.a. late interaction) architecture, which allows to leverage token-level matching information in biomedical entity linking by integrating an existing task-specific training objective and exploring active query expansion.
Background: Rare diseases affect an estimated 300 million people worldwide, yet the research needed to guide diagnosis and treatment is often fragmented across multiple unstructured literature sources. Natural history studies (NHS) are a key source of this evidence, but manually extracting structured information from N...
Kevin Li, E. Sid, Qian Zhu· medRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
