Beyond Agreement: Scoring Panel-Surfaced Biomedical Entity Candidates for Curator Triage 事件

Beyond Agreement: Scoring Panel-Surfaced Biomedical Entity Candidates for Curator Triage arXiv:2605.30826v1 Announce Type: new Abstract: Biomedical NER is deceptively simple for modern LLMs: plausible biomedical mentions are easy to surface, but corpus-convention correctness depends on annotation conventions, span boundaries, entity granularity, and type schemas. Multi-LLM agreement is a salience signal, not corpus-convention correctness. We introduce a candidate-level panel-output benchmark fo