arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.01831cs.CLcs.AIcs.LG
收藏

评估可解释的AI:哪些数学解释有助于用户预测模型行为?

Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?

UNC Chapel Hill(北卡罗来纳大学教堂山分校)

Peter Hase, Mohit Bansal

摘要:

近年来,解释机器学习模型的数学方法激增。我们进行了人类受试者测试,这是同类测试中的第一次,以隔离算法解释对模型可解释性,可模拟性的关键方面的影响,同时避免重要的混淆实验因素。当一个人可以根据新的输入预测其行为时,模型是可模拟的。通过文本和表格数据的两种模拟测试,我们评估了五种解释方法:(1)LIME,(2)锚,(3)决策边界,(4)原型模型,和(5)一个组合的方法,从每种方法的解释。在极少数情况下,发现方法有效性的明确证据:LIME提高了表格分类的可模拟性,我们的原型方法在反事实模拟测试中是有效的。我们也收集解释的主观评分,但我们没有发现评分可以预测解释的帮助程度。我们的研究结果提供了第一个可靠和全面的估计如何解释影响模拟性在各种解释方法和数据域。我们表明,(1)我们需要小心我们用来评估解释方法的指标,(2)目前的方法有很大的改进空间。我们所有的支持代码、数据和模型都可以在https://github.com/peterbhase/InterpretableNLP-ACL2020上公开获取。

英文摘要:

Algorithmic approaches to interpreting machine learning models have proliferated in recent years. We carry out human subject tests that are the first of their kind to isolate the effect of algorithmic explanations on a key aspect of model interpretability, simulatability, while avoiding important confounding experimental factors. A model is simulatable when a person can predict its behavior on new inputs. Through two kinds of simulation tests involving text and tabular data, we evaluate five explanations methods: (1) LIME, (2) Anchor, (3) Decision Boundary, (4) a Prototype model, and (5) a Composite approach that combines explanations from each method. Clear evidence of method effectiveness is found in very few cases: LIME improves simulatability in tabular classification, and our Prototype method is effective in counterfactual simulation tests. We also collect subjective ratings of explanations, but we do not find that ratings are predictive of how helpful explanations are. Our results provide the first reliable and comprehensive estimates of how explanations influence simulatability across a variety of explanation methods and data domains. We show that (1) we need to be careful about the metrics we use to evaluate explanation methods, and (2) there is significant room for improvement in current methods. All our supporting code, data, and models are publicly available at: https://github.com/peterbhase/InterpretableNLP-ACL2020

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。

↑