8 papers
ANCHOR-RE: An Agentic Neuro-Symbolic Framework for Grounded Biomedical Relation Extraction
Shufan Ming, Yikun Han, Gibong Hong +2
Biomedical relation extraction (BioRE) extracts structured knowledge from biomedical literature for applications such as knowledge base construction and hypothesis generation. Trad…
Herculean: An Agentic Benchmark for Financial Intelligence
Xueqing Peng, Zhuohan Xie, Yupeng Cao +60
As AI agents improve, the central question is no longer whether they can solve isolated well-defined financial tasks, but whether they can reliably carry out financial professional…
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…
ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?
Joey Chan, Yikun Han, Jingyuan Chen +8
Plain Language Summaries (PLS) aim to make research accessible to lay readers, but they are typically written in a one-size-fits-all style that ignores differences in readers' info…
MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability
Yikun Han, Joey Chan, Jingyuan Chen +3
Patient-clinician communication is an asymmetric-information problem: patients often do not disclose fears, misconceptions, or practical barriers unless clinicians elicit them skil…
A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge
Le Ma, Ran Zhang, Yikun Han +17
As high-dimensional vector data increasingly surpasses the processing capabilities of traditional database management systems, Vector Databases (VDBs) have emerged and become tight…