arXiv cs.AI· Marco Zullich, Emily Schiller, Ivan Gentile, David Dembinsky, Adriano Lucieri, Kilian G\"oller, Steffen Seitz·· 6 天前AI 评分17
无锚点的忠实性：一篇关于可解释 AI 忠实性指标与特征重要性结构性错位的立场论文
Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance
AI 导读
一篇立场论文指出，现有可解释 AI 忠实性指标存在五大缺陷，导致解释与模型之间的近似程度难以严格量化，或量化成本过高。作者认为 XAI 实际主要作为调试工具，而非提升信任的手段，反而助长对错误预测的过度依赖。论文提出四条研究路径以提升指标可靠性，成果在 IJCAI-ECAI 2026 XAI 研讨会发表。
正文 · 原文
Abstract:Explainable Artificial Intelligence (XAI) tools have often been presented as methods to increase trust in machine learning models by making aspects of their algorithms more human-understandable. However, evidence accumulated over the last decade points to an overall failure of this objective, instead promoting overreliance on incorrect predictions, which can subsequently lead to algorithmic aversion. Rather, XAI appears to function primarily as a debugging tool, useful for obtaining anecdotal insights into, for example, features learned by the model. One of the main issues underlying this limitation is that XAI methods often oversimplify the inner workings of the model, resulting in misalignment between the explanation and the model itself - a behavior referred to as unfaithfulness or infidelity. Faithfulness can be interpreted as the degree of approximation between an explanation and the model. Computing faithfulness in a rigorous manner would thus make it possible to quantify one of the various elements of trustworthiness of an explanation. However, existing metrics present significant limitations, making this quantification either infeasible or computationally expensive. In this position paper, we outline five major shortcomings of current faithfulness metrics and propose four possible avenues for research to bolster their reliability.
| Comments: | Presented at the IJCAI-ECAI 2026 Workshop on Explainable Artificial Intelligence (XAI) |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML) |
| Cite as: | arXiv:2610.12493 [cs.AI] |
| (or arXiv:2610.12493v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12493 arXiv-issued DOI via DataCite |
Submission history
From: Marco Zullich [view email]
[v1]
Thu, 24 Sep 2026 15:29:40 UTC (111 KB)
来源：arXiv cs.AI · arxiv.org