arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.07692cs.LG
收藏

证据树:高效的'系统2'搜索用于忠实的多模态接地

Tree-of-Evidence: Efficient "System 2" Search for Faithful Multimodal Grounding

Georgia Institute of Technology(佐治亚理工学院)

Micky C. Nnamdi, Benoit L. Marteau, Yishan Zhong, J. Ben Tamo, May D. Wang

AI总结:

本文提出Tree-of-Evidence算法,通过离散优化问题实现多模态模型的可解释性,通过证据瓶颈和束搜索生成可审计的证据集,保留高预测性能并提升决策一致性。

摘要:

大型多模态模型(LMMs)在高风险领域如医疗中取得最佳性能,但其推理过程仍不透明。当前的可解释性方法,如注意力机制或事后显著性,常无法忠实反映模型的决策过程,尤其是在整合异质模态如时间序列和文本时。我们引入Tree-of-Evidence(ToE),一种推理时间搜索算法,将可解释性视为离散优化问题。与依赖软注意力权重不同,ToE使用轻量级证据瓶颈对粗粒度数据组或单元(如生命体征窗口、报告句子)进行评分,并通过束搜索确定生成模型预测所需的紧凑证据集。我们在六个任务上评估ToE,涵盖三个数据集和两个领域:四个临床预测任务在MIMIC-IV上,eICU的跨中心验证,以及LEMMA-RCA上的非临床故障检测。ToE在保持预测性能的同时生成可审计的证据轨迹,在所有设置中保留超过98%的完整模型AUROC,仅需五个证据单元。在稀疏证据预算下,ToE在决策一致性和概率保真度误差方面优于其他方法。定性分析显示,ToE会根据情况调整搜索策略:它通常仅使用生命体征解决简单情况,而在生理信号模糊时选择性地纳入文本。因此,ToE提供了一种实用机制,通过揭示支持每个预测的离散证据单元来审计多模态模型。

英文摘要:

Large Multimodal Models (LMMs) achieve state-of-the-art performance in high-stakes domains like healthcare, yet their reasoning remains opaque. Current interpretability methods, such as attention mechanisms or post-hoc saliency, often fail to faithfully represent the model's decision-making process, particularly when integrating heterogeneous modalities like time-series and text. We introduce Tree-of-Evidence (ToE), an inference-time search algorithm that frames interpretability as a discrete optimization problem. Rather than relying on soft attention weights, ToE employs lightweight Evidence Bottlenecks that score coarse groups or units of data (e.g., vital-sign windows, report sentences) and performs a beam search to identify the compact evidence set required to reproduce the model's prediction. We evaluate ToE across six tasks spanning three datasets and two domains: four clinical prediction tasks on MIMIC-IV, cross-center validation on eICU, and non-clinical fault detection on LEMMA-RCA. ToE produces auditable evidence traces while maintaining predictive performance, retaining over 0.98 of full-model AUROC with as few as five evidence units across all settings. Under sparse evidence budgets, ToE achieves higher decision agreement and lower probability fidelity error than other approaches. Qualitative analyses show that ToE adapts its search strategy: it often resolves straightforward cases using only vitals, while selectively incorporating text when physiological signals are ambiguous. ToE therefore provides a practical mechanism for auditing multimodal models by revealing which discrete evidence units support each prediction.

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。

↑