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 2202.08979cs.HCcs.AIcs.LG
收藏

AI推荐信中信任度量化的响应转移范式

The Response Shift Paradigm to Quantify Human Trust in AI Recommendations

Imperial College London(帝国理工学院);MRC London Institute of Medical Sciences(英国医学研究理事会伦敦医学科学研究所)

Ali Shafti, Victoria Derks, Hannah Kay, A. Aldo Faisal

摘要:

可解释性、可解释性以及它们在多大程度上影响了人类对AI系统的信任,最终都是人类认知和机器学习的问题,但AI推荐的有效性和最终用户提供的信任通常不会得到定量评估。我们开发并验证了一个通用的人机交互范例,该范例量化了人工智能建议对人类决策的影响。在我们的范式中,我们向人类用户提出定量预测任务:要求他们给出第一反应,然后向他们提供人工智能的建议(和解释),然后要求人类用户提供更新的最终反应。最终和第一反应之间的差异构成了人类决策的转变或动摇,我们将其用作AI对人类的建议影响的指标,代表了他们对AI的信任。我们通过Amazon Mechanical Turk对数百名用户进行了评估,使用多分支实验,让用户面对好/差的AI系统,这些系统具有好的、差的或没有可解释性。我们的原理证明范式允许人们定量地比较快速增长的XAI/IAI方法对最终用户的影响,并开辟了(机器)学习信任的可能性。

英文摘要:

Explainability, interpretability and how much they affect human trust in AI systems are ultimately problems of human cognition as much as machine learning, yet the effectiveness of AI recommendations and the trust afforded by end-users are typically not evaluated quantitatively. We developed and validated a general purpose Human-AI interaction paradigm which quantifies the impact of AI recommendations on human decisions. In our paradigm we confronted human users with quantitative prediction tasks: asking them for a first response, before confronting them with an AI's recommendations (and explanation), and then asking the human user to provide an updated final response. The difference between final and first responses constitutes the shift or sway in the human decision which we use as metric of the AI's recommendation impact on the human, representing the trust they place on the AI. We evaluated this paradigm on hundreds of users through Amazon Mechanical Turk using a multi-branched experiment confronting users with good/poor AI systems that had good, poor or no explainability. Our proof-of-principle paradigm allows one to quantitatively compare the rapidly growing set of XAI/IAI approaches in terms of their effect on the end-user and opens up the possibility of (machine) learning trust.

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。

↑