English(EN) Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings

研究发现AI可解释性（XAI）的Shapley值基准与人类效用不符

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-24 15:38

一篇新论文探讨了可解释人工智能（XAI）方法，特别是Shapley值变体的评估，在欺诈检测等高风险场景中的应用。研究人员发现，XAI的标准量化指标与人类的理解或决策效用不符。尽管测试的XAI模型并未提高分析师的绩效，但它们确实增加了决策信心，引发了对自动化偏见的担忧。 AI

影响当前XAI的评估指标可能无法反映真实的、人类的效用，可能导致在关键决策中过度自信和自动化偏见。

排序理由关于XAI评估方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · In\^es Oliveira e Silva, S\'ergio Jesus, Iker Perez, Rita P. Ribeiro, Carlos Soares, Hugo Ferreira, Pedro Bizarro · 2026-04-27 04:00

重新审视XAI评估：高风险场景下Shapley基准的人本审计

arXiv:2604.22662v1 Announce Type: new Abstract: Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little consensus on practical deployment. While theoretical differences are well-documen…
arXiv cs.AI TIER_1 English(EN) · Pedro Bizarro · 2026-04-24 15:38

重新审视XAI评估：高风险场景下Shapley基准的人本审计

Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little consensus on practical deployment. While theoretical differences are well-documented, evaluation remains reliant on quantitative …