让临床模型决策可审计，抑制无关文本特征提升可靠性
Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction
- 用稀疏自编码器提取中间层可解释特征，定位文本中的干扰模式
- 在MIMIC-IV数据集上预测死亡率，准确率优于基线且接近顶级大模型
- 生成每条预测的临床概念依据和被抑制的干扰项，便于医生审核
临床语言模型虽在院内数据上表现优异，但在部署后因依赖病历模板、分隔符等非患者状态相关特征而失效。本文提出CAST（概念引导的特征抑制微调）框架，基于稀疏自编码器从Transformer中间激活中提取稀疏、可人工审计的特征，通过大模型辅助解释与ICD-10检索约束对特征进行标注，微调阶段通过残差减法抑制已验证的干扰特征，并提供事后每个概念的归因分析。在MIMIC-IV出院记录死亡率预测任务中，CAST优于对应微调基线模型，在性能上仍可媲美强大学习模型，同时生成支持预测的临床概念依据及训练中被抑制的干扰概念，实现模型决策的特征级审计追踪。
原文摘要 · Abstract (English)
Clinical language models can achieve strong in-hospital accuracy yet fail under deployment shifts because they exploit note-specific artifacts (e.g., templates, separators, boilerplate) that do not reflect patient state. We propose CAST (Concept-guided Artifact Suppression Tuning), an SAE-based framework for auditable clinical text classification. CAST uses Sparse Autoencoders to expose sparse, human-auditable features from intermediate Transformer activations, labels SAE latents with an LLM-assisted interpretation pipeline and ICD-10 retrieval constraints, suppresses verified artifact latents via residual subtraction during fine-tuning, and provides post-hoc per-concept attributions for auditing model decisions. On MIMIC-IV discharge-note mortality prediction, CAST improves over its corresponding fine-tuned encoder baselines and remains competitive with strong LLM baselines, while producing a feature-level audit trail of the clinical concepts that support each prediction and the artifact concepts suppressed during training.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。