Real-world documents distribute evidence across text, tables, figures, and captions within complex page layouts. Answering complex questions over such documents therefore requires more than retrieving relevant passages: systems must recover the evidence topology that connects heterogeneous evidence units. Existing Grap...
Ruo-Chi Li, Jian-Zhe Lin, Haoxuan Zhang et al.· 0 citations
Synthetic clinical data generation with large language models addresses the scarcity that limits cancer staging research, but oncology hallucinations are categorically harmful: one clinically impossible staging assignment contaminates every downstream model trained on it. Neuro-symbolic pipelines validate during genera...
Laxmigayathri Challa, Yuhan Zhou, Ana Cleveland et al.· 0 citations
This study finds that existing MCN benchmarks present data quality issues and underexplored data fusion potential, and data quality enhancement and LLM-based controlled-variety data augmentation help alleviate overlapping phrases and long-tail issues.
Yuhan Zhou, Ruochi Li, Ana Cleveland et al.· Journal of Biomedical Inform...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.