你的模型是不公平的,你甚至意识到吗? 理解和对可解释性的信任之间的反向关系 偏见的ML模型的可视化可解释性
IEEE transactions on visualization and computer graphics
|December 5, 2025
概括
机器学习 (ML) 的可解释性可视化可以悖论地通过增加感知偏差来减少信任. 提高模型公平性或调整可视化可以增强信任,即使理解能力很高.
科学领域:
- 机器学习 机器学习
- 人与计算机的交互
- 负责的人工智能
背景情况:
- 机器学习 (ML) 系统很普遍,但却表现出有偏见的行为,影响用户的信任和互动.
- 利益相关者对机器学习系统的信任和看法在不同背景下有很大差异.
- 可解释性可视化对于理解ML模型的行为,理解和信任至关重要.
研究的目的:
- 调查可解释性可视化,并创建设计特征的分类学.
- 通过用户研究来评估最先进的ML可解释性可视化工具 (LIME,SHAP,CP,Anchors,ELI5).
- 测量可视化设计特征对非专家ML用户的理解,偏见感知和信任的影响.
主要方法:
- 进行了用户研究,评估了五种可解释性可视化工具.
- 为可解释性可视化开发了设计特征的分类学.
- 与可视化设计和模型公平性相关的测量理解,偏见感知和信任.
主要成果:
- 在理解和信任之间发现了反向关系:更高的理解导致了更低的信任.
- 偏见感知调解了这种关系:更容易理解的可视化增加了感知偏见,减少了信任.
- 可视化设计显著影响理解,感知偏见和信任 (p < 0.001).
结论:
- 可解释性可视化设计可以被操纵来控制理解,偏见感知和信任.
- 通过公平性改进或可视化调整来减少感知模型偏差,即使在高度理解的情况下,也会增加信任.
- 这些发现促进了对理解-信任动态的理解,以及可视化在负责任的ML中的作用.
相关概念视频
Bias
7.2K
Bias refers to any tendency that prevents a question from being considered unprejudiced. In research, bias occurs when one outcome or answer is selected or encouraged over others in sampling or testing. Bias can occur during any research phase, including study design, data collection, analysis, and publication.
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
7.2K
Hindsight Biases
4.2K
Hindsight bias leads you to believe that the event you just experienced was predictable, even though it really wasn’t. In other words, you knew all along that things would turn out the way they did. Can you relate this to the phrase "Hindsight is 20/20" now?
4.2K
Cause and Effect
12.0K
While variables are sometimes correlated because one does cause the other, it could also be that some other factor, a confounding variable, is actually causing the systematic movement in our variables of interest. For instance, as sales in ice cream increase, so does the overall rate of crime. Is it possible that indulging in your favorite flavor of ice cream could send you on a crime spree? Or, after committing crime do you think you might decide to treat yourself to a cone?
12.0K
Confirmation Biases
7.6K
The confirmation bias is the tendency to focus on information that confirms our existing beliefs and ignore information that is inconsistent with our expectations. For example, if you think that your professor is not very nice, you notice all of the instances of rude behavior exhibited by the professor while ignoring the countless pleasant interactions he is involved in on a daily basis. Have you ever fallen prey to the confirmation bias, either as the source or target of such bias?
7.6K
Fundamental Attribution Error
13.7K
According to some social psychologists, people tend to overemphasize internal factors as explanations—or attributions—for the behavior of other people. They tend to assume that the behavior of another person is a trait of that person, and to underestimate the power of the situation on the behavior of others. They tend to fail to recognize when the behavior of another is due to situational variables, and thus to the person’s state. This erroneous assumption is...
13.7K
Theory of Attribution II: Kelley's Covariation Theory
465
Attribution theory plays a crucial role in social psychology, helping to explain how individuals interpret the causes of behavior. One prominent model within this field is Harold Kelley's covariation theory, which provides a systematic approach to determining whether internal traits or external circumstances drive a person's actions. The model posits that individuals rely on three key types of information—consensus, consistency, and distinctiveness—to make these judgments.Consensus:...
465
