让大模型在临床文本中精准定位不确定词元，提升医疗决策可信度。
Reverse Probing: Supervised Token-level Uncertainty Quantification for Large Language Models in Clinical Text
- 通过反向探针法从已有标注摘要中提取模型内部激活信号，实现词元级不确定性量化。
- 在两个专家标注数据集上超越8个基线方法，最高AUPRC提升4倍，推理速度更快。
- 发现能量差和邻近上下文是跨模型最稳定的不确定预测因子，适合医疗领域应用。
随着大语言模型在临床文本中的广泛应用，使其能可靠地自我标识不确定性变得至关重要。现有不确定性量化（UQ）方法多针对开放域生成任务，难以在长篇临床文本中实现词元或片段级别的不确定性定位。本文提出首个专为临床摘要设计的UQ框架——反向探针（Reverse Probing），直接利用预有的标注摘要，不依赖重新采样，将文本视为对模型内部状态的探针，从四类内部激活中提取不确定性信号。在两个专家标注的临床数据集上评估，该方法全面优于8种适配基线，在所有指标上表现更优，最高AUPRC提升4倍，同时降低推理时间和计算开销。特征分析表明，能量差（delta energy）与邻近上下文是跨模型最一致的预测因子。研究为理解模型对无支持临床内容的内部响应提供了可解释性洞察。
原文摘要 · Abstract (English)
As large language models are increasingly deployed for clinical text, ensuring they can reliably signal their own uncertainty becomes critical. Most existing uncertainty quantification (UQ) methods are designed for open-domain generation and cannot localize uncertainty at the token or span level in long clinical text. We propose Reverse Probing, the first UQ framework specialized for clinical summarization, which estimates token-level uncertainty directly from pre-existing labeled summaries. Rather than sampling new outputs, Reverse Probing treats the text as a probe into the model's internal state, extracting uncertainty signals from four categories of internal activations. We evaluate on two expert-annotated clinical datasets and outperform eight adapted baselines on all metrics, achieving up to 4 times higher AUPRC while reducing inference time and computational costs. Feature analysis reveals that delta energy and neighborhood context are the most consistent predictors across all models. This study offers interpretable insights into how models internally respond to unsupported clinical content.
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。