6 papers
ANCHOR-RE: An Agentic Biomedical Relation Extraction Framework with Retrieval Augmentation and Error-Driven Verification
Shufan Ming, Yikun Han, Gibong Hong +2
Biomedical relation extraction (BioRE) supports knowledge graph construction and hypothesis generation. In real-world settings, most candidate entity pairs are unrelated. Symbolic…
Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations
Shufan Ming, Joe D. Menke, Neil R. Smalheiser +1
Accurately and consistently indexing biomedical literature by publication type and study design is essential for supporting evidence synthesis and knowledge discovery. Prior work o…
Divide-Prompt-Refine: a Training-Free, Structure-Aware Framework for Biomedical Abstract Generation
Sylvey Lin, Joe Menke, Shufan Ming +3
Biomedical abstracts play a critical role in downstream NLP applications, such as information retrieval, biocuration, and biomedical knowledge discovery. However, a non-trivial num…
When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question Answering
Yikun Han, Mengfei Lan, Halil Kilicoglu
Biomedical retrieval-augmented large language models (LLMs) often face evidence that is incomplete, misleading, or internally contradictory, yet evaluation usually emphasizes answe…
BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels
Mengfei Lan, Lecheng Zheng, Halil Kilicoglu
Effective biomedical information retrieval requires modeling domain semantics and hierarchical relationships among biomedical texts. Existing biomedical generative retrievers build…
Goals and Strategies for the Indexing of Publication Types and Study Designs
Neil R. Smalheiser, Joe D. Menke, Arthur W. Holt +2
Objectives. Major research and implementation efforts have been devoted to indexing articles according to the major topics discussed, but much less effort to indexing their publica…