skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Friday, November 15 until 2:00 AM ET on Saturday, November 16 due to maintenance. We apologize for the inconvenience.


Title: Selective Explanations: Leveraging Human Input to Align Explainable AI

While a vast collection of explainable AI (XAI) algorithms has been developed in recent years, they have been criticized for significant gaps with how humans produce and consume explanations. As a result, current XAI techniques are often found to be hard to use and lack effectiveness. In this work, we attempt to close these gaps by making AI explanations selective ---a fundamental property of human explanations---by selectively presenting a subset of model reasoning based on what aligns with the recipient's preferences. We propose a general framework for generating selective explanations by leveraging human input on a small dataset. This framework opens up a rich design space that accounts for different selectivity goals, types of input, and more. As a showcase, we use a decision-support task to explore selective explanations based on what the decision-maker would consider relevant to the decision task. We conducted two experimental studies to examine three paradigms based on our proposed framework: in Study 1, we ask the participants to provide critique-based or open-ended input to generate selective explanations (self-input). In Study 2, we show the participants selective explanations based on input from a panel of similar users (annotator input). Our experiments demonstrate the promise of selective explanations in reducing over-reliance on AI and improving collaborative decision making and subjective perceptions of the AI system, but also paint a nuanced picture that attributes some of these positive effects to the opportunity to provide one's own input to augment AI explanations. Overall, our work proposes a novel XAI framework inspired by human communication behaviors and demonstrates its potential to encourage future work to make AI explanations more human-compatible.

 
more » « less
Award ID(s):
2126602 2040989
NSF-PAR ID:
10491344
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
Association for Computing Machinery
Date Published:
Journal Name:
Proceedings of the ACM on Human-Computer Interaction
Volume:
7
Issue:
CSCW2
ISSN:
2573-0142
Page Range / eLocation ID:
1 to 35
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Recent years have witnessed the growing literature in empirical evaluation of explainable AI (XAI) methods. This study contributes to this ongoing conversation by presenting a comparison on the effects of a set of established XAI methods in AI-assisted decision making. Based on our review of previous literature, we highlight three desirable properties that ideal AI explanations should satisfy — improve people’s understanding of the AI model, help people recognize the model uncertainty, and support people’s calibrated trust in the model. Through three randomized controlled experiments, we evaluate whether four types of common model-agnostic explainable AI methods satisfy these properties on two types of AI models of varying levels of complexity, and in two kinds of decision making contexts where people perceive themselves as having different levels of domain expertise. Our results demonstrate that many AI explanations do not satisfy any of the desirable properties when used on decision making tasks that people have little domain expertise in. On decision making tasks that people are more knowledgeable, the feature contribution explanation is shown to satisfy more desiderata of AI explanations, even when the AI model is inherently complex. We conclude by discussing the implications of our study for improving the design of XAI methods to better support human decision making, and for advancing more rigorous empirical evaluation of XAI methods. 
    more » « less
  2. AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against some protected group, explanations may include features that demonstrate this bias, but when biases are realized through proxy features, the relationship between this proxy feature and the protected one may be less clear to a human. In this work, we study the effect of the presence of protected and proxy features on participants’ perception of model fairness and their ability to improve demographic parity over an AI alone. Further, we examine how different treatments—explanations, model bias disclosure and proxy correlation disclosure—affect fairness perception and parity. We find that explanations help people detect direct but not indirect biases. Additionally, regardless of bias type, explanations tend to increase agreement with model biases. Disclosures can help mitigate this effect for indirect biases, improving both unfairness recognition and decision-making fairness. We hope that our findings can help guide further research into advancing explanations in support of fair human-AI decision-making. 
    more » « less
  3. The rise of complex AI systems in healthcare and other sectors has led to a growing area of research called Explainable AI (XAI) designed to increase transparency. In this area, quantitative and qualitative studies focus on improving user trust and task performance by providing system- and prediction-level XAI features. We analyze stakeholder engagement events (interviews and workshops) on the use of AI for kidney transplantation. From this we identify themes which we use to frame a scoping literature review on current XAI features. The stakeholder engagement process lasted over nine months covering three stakeholder group's workflows, determining where AI could intervene and assessing a mock XAI decision support system. Based on the stakeholder engagement, we identify four major themes relevant to designing XAI systems – 1) use of AI predictions, 2) information included in AI predictions, 3) personalization of AI predictions for individual differences, and 4) customizing AI predictions for specific cases. Using these themes, our scoping literature review finds that providing AI predictions before, during, or after decision-making could be beneficial depending on the complexity of the stakeholder's task. Additionally, expert stakeholders like surgeons prefer minimal to no XAI features, AI prediction, and uncertainty estimates for easy use cases. However, almost all stakeholders prefer to have optional XAI features to review when needed, especially in hard-to-predict cases. The literature also suggests that providing both system and prediction-level information is necessary to build the user's mental model of the system appropriately. Although XAI features improve users' trust in the system, human-AI team performance is not always enhanced. Overall, stakeholders prefer to have agency over the XAI interface to control the level of information based on their needs and task complexity. We conclude with suggestions for future research, especially on customizing XAI features based on preferences and tasks. 
    more » « less
  4. Explanations promise to bridge the gap between humans and AI, yet it remains difficult to achieve consistent improvement in AI-augmented human decision making. The usefulness of AI explanations depends on many factors, and always showing the same type of explanation in all cases is suboptimal—so is relying on heuristics to adapt explanations for each scenario. We propose learning to explain”selectively”: for each decision that the user makes, we use a model to choose the best explanation from a set of candidates and update this model with feedback to optimize human performance. We experiment on a question answering task, Quizbowl, and show that selective explanations improve human performance for both experts and crowdworkers. 
    more » « less
  5. While EXplainable Artificial Intelligence (XAI) approaches aim to improve human-AI collaborative decision-making by improving model transparency and mental model formations, experiential factors associated with human users can cause challenges in ways system designers do not anticipate. In this paper, we first showcase a user study on how anchoring bias can potentially affect mental model formations when users initially interact with an intelligent system and the role of explanations in addressing this bias. Using a video activity recognition tool in cooking domain, we asked participants to verify whether a set of kitchen policies are being followed, with each policy focusing on a weakness or a strength. We controlled the order of the policies and the presence of explanations to test our hypotheses. Our main finding shows that those who observed system strengths early-on were more prone to automation bias and made significantly more errors due to positive first impressions of the system, while they built a more accurate mental model of the system competencies. On the other hand, those who encountered weaknesses earlier made significantly fewer errors since they tended to rely more on themselves, while they also underestimated model competencies due to having a more negative first impression of the model. Motivated by these findings and similar existing work, we formalize and present a conceptual model of user’s past experiences that examine the relations between user’s backgrounds, experiences, and human factors in XAI systems based on usage time. Our work presents strong findings and implications, aiming to raise the awareness of AI designers towards biases associated with user impressions and backgrounds. 
    more » « less