Cheap Ways of Extracting Clinical Markers from Texts

arXiv:2403.11227v1 Announce Type: cross
Abstract: This paper describes the work of the UniBuc Archaeology team for CLPsych's 2024 Shared Task, which involved finding evidence within the text supporting the assigned suicide risk level. Two types of evidence were required: highlights (extracting relevant spans within the text) and summaries (aggregating evidence into a synthesis). Our work focuses on evaluating Large Language Models (LLM) as opposed to an alternative method that is much more memory and resource efficient. The first approach employs …

abstract archaeology arxiv clinical cs.cl cs.lg evidence highlights paper risk suicide team text type types work