发表机构
University of Virginia（弗吉尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究开发了一种基于拓扑的多模态对齐测试，以提升不透明AI模型部署、选择与比较的可解释性，助力AI对齐测试与语义空间表征。
AI 中文摘要
现代不透明AI模型以性能优先于可解释性，这使得模型测试变得困难。然而，对模型嵌入空间进行的形式化统计测试能够对语义结构、概念分离和知识图谱对齐提供鲁棒表征。模型开发者将受益于一种利用人工整理的知识结构来测试对齐的模型比较技术。即使是相对简单的任务，其输入空间的规模也促使我们需要对齐检查来补充标准结果推理。本研究开发并验证了一种基于拓扑的多模态对齐测试，以使不透明模型的部署、选择和比较更具可解释性。这些方法还与可能性理论以及从数据到部署的统一决策理论框架建立了直观联系。
英文摘要
Modern opaque AI models prize performance over interpretability, which makes testing difficult. However, formal statistical tests conducted on a model's embedding space can provide robust characterizations of semantic structure, concept separation, and knowledge graph alignment. Model developers would benefit from a model comparison technique that leverages human-curated knowledge structures to test alignment. The scale of the input space for even relatively simple tasks motivates the need for alignment checks that augment standard outcome reasoning. This work develops and demonstrates a topology-based multi-modal alignment test to make deployment, selection, and comparison of opaque models more interpretable. These methods also offer an intuitive connection to possibility theory and a unified decision theoretic framework from data to deployment.
CommentsCode available at github.com/tylerashoff/persiscope (PyPI: persiscope)
