arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.04764cs.AI
收藏

人类认知偏差在基于解释的交互中的体现:会话内与会话间顺序效应的案例

Human Cognitive Biases in Explanation-Based Interaction: The Case of Within and Between Session Order Effect

CIMeC, University of Trento(CIMeC、特伦托大学)

Dario Pesenti, Alessandro Bogani, Katya Tentori, Stefano Teso

AI总结:

研究探讨了基于解释的交互学习中顺序效应的影响,发现其在会话内有显著影响,但不会对反馈质量造成重大问题。

摘要:

解释性交互学习(XIL)是一种强大的交互学习框架,旨在通过与AI模型的解释进行交互,使用户能够自定义和纠正AI模型。简而言之,XIL算法会选择一些AI模型做出决策的项目(例如图像及其标签),并将它们呈现给用户,同时提供相应的解释(例如驱动模型决策的图像区域)。然后,用户为这些解释提供纠正反馈,算法利用这些反馈来改进模型。尽管在调试任务中显示出潜力,但最近的研究提出了担忧,即解释交互可能会触发顺序效应,这是一种众所周知的认知偏差,其中所呈现项目的顺序会影响用户的信任,以及关键的反馈质量。我们认为这些研究并不完全具有说服力,因为实验设计和任务与常见的XIL使用案例存在显著差异,这使得解释变得更加复杂。为了澄清顺序效应与解释交互之间的相互作用,我们进行了两项更大规模的用户研究(n=713),旨在模仿常见的XIL任务。具体而言,我们通过操纵正确和错误解释的呈现顺序来评估顺序效应,无论是会话内还是会话间。顺序效应在用户对模型的同意上产生了有限但显著的影响(即对信任的衡量行为指标),并且只有在会话内检查时才产生影响,而不是在会话间。用户反馈的质量总体上令人满意,顺序效应在两个实验中对反馈的影响仅是小而不一致的。总体而言,我们的发现表明,顺序效应并不对XIL方法的成功应用构成重大问题。更广泛地说,我们的工作为理解AI中的人类因素做出了贡献。

英文摘要:

Explanatory Interactive Learning (XIL) is a powerful interactive learning framework designed to enable users to customize and correct AI models by interacting with their explanations. In a nutshell, XIL algorithms select a number of items on which an AI model made a decision (e.g. images and their tags) and present them to users, together with corresponding explanations (e.g. image regions that drive the model's decision). Then, users supply corrective feedback for the explanations, which the algorithm uses to improve the model. Despite showing promise in debugging tasks, recent studies have raised concerns that explanatory interaction may trigger order effects, a well-known cognitive bias in which the sequence of presented items influences users' trust and, critically, the quality of their feedback. We argue that these studies are not entirely conclusive, as the experimental designs and tasks employed differ substantially from common XIL use cases, complicating interpretation. To clarify the interplay between order effects and explanatory interaction, we ran two larger-scale user studies (n = 713 total) designed to mimic common XIL tasks. Specifically, we assessed order effects both within and between debugging sessions by manipulating the order in which correct and wrong explanations are presented to participants. Order effects had a limited, through significant impact on users' agreement with the model (i.e., a behavioral measure of their trust), and only when examined withing debugging sessions, not between them. The quality of users' feedback was generally satisfactory, with order effects exerting only a small and inconsistent influence in both experiments. Overall, our findings suggest that order effects do not pose a significant issue for the successful employment of XIL approaches. More broadly, our work contributes to the ongoing efforts for understanding human factors in AI.

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。

↑