虚假关联及其之外：理解与缓解大型语言模型在 SDOH 抽取中的捷径学习
Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models
AI总结：
研究大型语言模型在 SDOH 抽取中因依赖表面线索导致的虚假预测及性别差异问题，并评估提示工程与思维链等缓解策略以提升模型可靠性。
摘要：
从临床文本中提取健康的社会决定因素（SDOH）对下游医疗分析至关重要。尽管大型语言模型（LLMs）展现出潜力，但它们可能依赖表面线索导致虚假预测。使用 SHAC（Social History Annotation Corpus）数据集的 MIMIC 部分，并以酒精提取为案例研究，我们证明酒精或吸烟的提及会错误诱导模型在不存在酒精时预测当前/既往酒精使用，同时揭示了模型性能中令人担忧的性别差异。我们进一步评估了提示工程和思维链推理等缓解策略以减少这些假阳性，为提升 LLM 在医疗领域的可靠性提供了见解。
英文摘要：
Social determinants of health (SDOH) extraction from clinical text is critical for downstream healthcare analytics. Although large language models (LLMs) have shown promise, they may rely on superficial cues leading to spurious predictions. Using the MIMIC portion of the SHAC (Social History Annotation Corpus) dataset and focusing on drug status extraction as a case study, we demonstrate that mentions of alcohol or smoking can falsely induce models to predict current/past drug use where none is present, while also uncovering concerning gender disparities in model performance. We further evaluate mitigation strategies - such as prompt engineering and chain-of-thought reasoning - to reduce these false positives, providing insights into enhancing LLM reliability in health domains.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
