用微调大模型生成可解释的健康干预方案，提升模型鲁棒性。
Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation
- 微调大模型生成符合临床实际的反事实干预建议。
- 在标签稀缺下使模型F1值平均恢复20%性能。
- 适合数字健康、医疗决策支持系统开发者使用。
反事实解释（CFE）通过识别最小且可操作的改变来调整机器学习预测，具备以人为本的可解释性。因此，反事实可用于（i）异常预防干预设计，（ii）增强数据以训练更稳健的模型。本文全面评估了大语言模型（LLMs）在生成反事实方面的表现，包括GPT-4（零样本和少样本）、BioMistral-7B与LLaMA-3.1-8B（预训练及微调版本）。基于多模态AI-READI临床数据集，从干预质量、特征多样性与增强有效性三方面评估。微调后的LLaMA-3.1-8B生成的反事实具有高达99%的合理性、0.99的有效性，并能实现现实可行的行为调整。在标签稀缺条件下用于数据增强时，显著恢复分类器性能，平均提升20% F1得分。相比优化基线（DiCE、CFNOW、NICE），LLMs提供灵活、模型无关的方法，生成更具临床可操作性和语义一致性的反事实。本研究证明，大模型驱动的反事实在传感器驱动的数字健康领域中，兼具可解释干预设计与高效数据训练潜力。影响：SenseCF微调大模型生成有效、代表性反事实，补充少数类样本，提升模型训练效果与预测性能。
原文摘要 · Abstract (English)
Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine learning model's prediction. Therefore, CFs can be used as (i) interventions for abnormality prevention and (ii) augmented data for training robust models. We conduct a comprehensive evaluation of CF generation using large language models (LLMs), including GPT-4 (zero-shot and few-shot) and two open-source models-BioMistral-7B and LLaMA-3.1-8B, in both pretrained and fine-tuned configurations. Using the multimodal AI-READI clinical dataset, we assess CFs across three dimensions: intervention quality, feature diversity, and augmentation effectiveness. Fine-tuned LLMs, particularly LLaMA-3.1-8B, produce CFs with high plausibility (up to 99%), strong validity (up to 0.99), and realistic, behaviorally modifiable feature adjustments. When used for data augmentation under controlled label-scarcity settings, LLM-generated CFs substantially restore classifier performance, yielding an average 20% F1 recovery across three scarcity scenarios. Compared with optimization-based baselines such as DiCE, CFNOW, and NICE, LLMs offer a flexible, model-agnostic approach that generates more clinically actionable and semantically coherent counterfactuals. Overall, this work demonstrates the promise of LLM-driven counterfactuals for both interpretable intervention design and data-efficient model training in sensor-based digital health. Impact: SenseCF fine-tunes an LLM to generate valid, representative counterfactual explanations and supplement minority class in an imbalanced dataset for improving model training and boosting model robustness and predictive performance
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。