arXiv：cs.LG· Jesse C. Cresswell·· 10 小时前
可信 AI 必须考虑各维度之间的交互影响
Trustworthy AI Must Account for Interactions
AI 导读
NeurIPS 2026 立场论文指出，公平、隐私、鲁棒性、可解释性与不确定性量化等可信 AI 维度常相互冲突，例如对模型训练施加差分隐私会放大偏见、损害公平性。论文系统梳理了这五个维度两两组合间的负面交互，认为孤立改进一两个维度的现有做法不够，可信 AI 研究需采取整体视角，并给出了研究者与从业者的实践建议。
正文
Abstract:Trustworthy AI encompasses many aspirational aspects for aligning AI systems with human values, including fairness, privacy, robustness, explainability, and uncertainty quantification. The ultimate goal of Trustworthy AI research is to achieve all aspects simultaneously. However, efforts to enhance one aspect often introduce unintended trade-offs that negatively impact others. In this position paper, we review notable approaches to five aspects and systematically consider every pair, detailing the negative interactions that can arise. For example, applying differential privacy to model training can amplify biases, undermining fairness. Drawing on these findings, we take the position that current research practices of improving one or two aspects in isolation are insufficient. Instead, research on Trustworthy AI must account for interactions between aspects and adopt a holistic view across all relevant axes at once. We offer recommendations for how researchers can work towards integrated trust, and provide guidance for practitioners to manage interactions today.
| Comments: | NeurIPS 2026 Position Paper Track |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2504.07170 [cs.LG] |
| (or arXiv:2504.07170v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2504.07170 arXiv-issued DOI via DataCite |
Submission history
From: Jesse Cresswell [view email]
[v1]
Wed, 9 Apr 2025 18:00:00 UTC (74 KB)
[v2]
Mon, 3 Nov 2025 01:42:55 UTC (74 KB)
[v3]
Tue, 13 Oct 2026 18:48:52 UTC (46 KB)
来源：arXiv：cs.LG · arxiv.org