ACM Transactions on Interactive Intelligent Systems最新文献

Recently, eXplainable AI (XAI) research has focused on the use of counterfactual explanations to address interpretability, algorithmic recourse, and bias in AI system decision-making. The developers of these algorithms claim they meet user requirements in generating counterfactual explanations with “plausible”, “actionable” or “causally important” features. However, few of these claims have been tested in controlled psychological studies. Hence, we know very little about which aspects of counterfactual explanations really help users understand the decisions of AI systems. Nor do we know whether counterfactual explanations are an advance on more traditional causal explanations that have a longer history in AI (e.g., in expert systems). Accordingly, we carried out three user studies to (i) test a fundamental distinction in feature-types, between categorical and continuous features, and (ii) compare the relative effectiveness of counterfactual and causal explanations. The studies used a simulated, automated decision-making app that determined safe driving limits after drinking alcohol, based on predicted blood alcohol content, where users’ responses were measured objectively (using predictive accuracy) and subjectively (using satisfaction and trust judgments). Study 1 (N = 127) showed that users understand explanations referring to categorical features more readily than those referring to continuous features. It also discovered a dissociation between objective and subjective measures: counterfactual explanations elicited higher accuracy than no-explanation controls but elicited no more accuracy than causal explanations, yet counterfactual explanations elicited greater satisfaction and trust than causal explanations. In Study 2 (N = 136) we transformed the continuous features of presented items to be categorical (i.e., binary) and found that these converted features led to highly accurate responding. Study 3 (N = 211) explicitly compared matched items involving either mixed features (i.e., a mix of categorical and continuous features) or categorical features (i.e., categorical and categorically-transformed continuous features), and found that users were more accurate when categorically-transformed features were used instead of continuous ones. It also replicated the dissociation between objective and subjective effects of explanations. The findings delineate important boundary conditions for current and future counterfactual explanation methods in XAI.

Storytelling is an integral part of human culture and significantly impacts cognitive and socio-emotional development and connection. Despite the importance of interactive visual storytelling, the process of creating such content requires specialized skills and is labor-intensive. This paper introduces ID.8, an open-source system designed for the co-creation of visual stories with generative AI. We focus on enabling an inclusive storytelling experience by simplifying the content creation process and allowing for customization. Our user evaluation confirms a generally positive user experience in domains such as enjoyment and exploration, while highlighting areas for improvement, particularly in immersiveness, alignment, and partnership between the user and the AI system. Overall, our findings indicate promising possibilities for empowering people to create visual stories with generative AI. This work contributes a novel content authoring system, ID.8, and insights into the challenges and potential of using generative AI for multimedia content creation.

Providing system-generated explanations for recommendations represents an important step towards transparent and trustworthy recommender systems. Explainable recommender systems provide a human-understandable rationale for their outputs. Over the past two decades, explainable recommendation has attracted much attention in the recommender systems research community. This paper aims to provide a comprehensive review of research efforts on visual explanation in recommender systems. More concretely, we systematically review the literature on explanations in recommender systems based on four dimensions, namely explanation aim, explanation scope, explanation method, and explanation format. Recognizing the importance of visualization, we approach the recommender system literature from the angle of explanatory visualizations, that is using visualizations as a display style of explanation. As a result, we derive a set of guidelines that might be constructive for designing explanatory visualizations in recommender systems and identify perspectives for future work in this field. The aim of this review is to help recommendation researchers and practitioners better understand the potential of visually explainable recommendation research and to support them in the systematic design of visual explanations in current and future recommender systems.

This paper aims to develop a semi-formal representation for Human-AI (HAI) interactions, by building a set of interaction primitives which can specify the information exchanges between users and AI systems during their interaction. We show how these primitives can be combined into a set of interaction patterns which can capture common interactions between humans and AI/ML models. The motivation behind this is twofold: firstly, to provide a compact generalisation of existing practices for the design and implementation of HAI interactions; and secondly, to support the creation of new interactions by extending the design space of HAI interactions. Taking into consideration frameworks, guidelines and taxonomies related to human-centered design and implementation of AI systems, we define a vocabulary for describing information exchanges based on the model’s characteristics and interactional capabilities. Based on this vocabulary, a message passing model for interactions between humans and models is presented, which we demonstrate can account for existing HAI interaction systems and approaches. Finally, we build this into design patterns which can describe common interactions between users and models, and we discuss how this approach can be used towards a design space for HAI interactions that creates new possibilities for designs as well as keeping track of implementation issues and concerns.

In response to diverse perspectives on Artificial General Intelligence (AGI), ranging from potential safety and ethical concerns to more extreme views about the threats it poses to humanity, this research presents a generic method to gauge the reasoning capabilities of Artificial Intelligence (AI) models as a foundational step in evaluating safety measures. Recognizing that AI reasoning measures cannot be wholly automated, due to factors such as cultural complexity, we conducted an extensive examination of five commercial Generative Pre-trained Transformers (GPTs), focusing on their comprehension and interpretation of culturally intricate contexts. Utilizing our novel “Reasoning and Value Alignment Test”, we assessed the GPT models’ ability to reason in complex situations and grasp local cultural subtleties. Our findings have indicated that, although the models have exhibited high levels of human-like reasoning, significant limitations remained, especially concerning the interpretation of cultural contexts. This paper also explored potential applications and use-cases of our Test, underlining its significance in AI training, ethics compliance, sensitivity auditing, and AI-driven cultural consultation. We concluded by emphasizing its broader implications in the AGI domain, highlighting the necessity for interdisciplinary approaches, wider accessibility to various GPT models, and a profound understanding of the interplay between GPT reasoning and cultural sensitivity.

Reinforcement Learning (RL) is crucial in decision optimization, but its inherent complexity often presents challenges in interpretation and communication. Building upon AutoDOViz — an interface that pushed the boundaries of Automated RL for Decision Optimization — this paper unveils an open-source expansion with a web-based platform for RL. Our work introduces a taxonomy of RL visualizations and launches a dynamic web platform, leveraging backend flexibility for AutoRL frameworks like ARLO and Svelte.js for a smooth interactive user experience in the front end. Since AutoDOViz is not open-source, we present AutoRL X, a new interface designed to visualize RL processes. AutoRL X is shaped by the extensive user feedback and expert interviews from AutoDOViz studies, and it brings forth an intelligent interface with real-time, intuitive visualization capabilities that enhance understanding, collaborative efforts, and personalization of RL agents. Addressing the gap in accurately representing complex real-world challenges within standard RL environments, we demonstrate our tool's application in healthcare, explicitly optimizing brain stimulation trajectories. A user study contrasts the performance of human users optimizing electric fields via a 2D interface with RL agents’ behavior that we visually analyze in AutoRL X, assessing the practicality of automated RL. All our data and code is openly available at: https://github.com/lorifranke/autorlx.

Motivations: Recent research has emerged on generally how to improve AI products’ Human-AI Interaction (HAI) User Experience (UX), but relatively little is known about HAI-UX inclusivity. For example, what kinds of users are supported, and who are left out? What product changes would make it more inclusive?

Objectives: To help fill this gap, we present an approach to measuring what kinds of diverse users an AI product leaves out and how to act upon that knowledge. To bring actionability to the results, the approach focuses on users’ problem-solving diversity. Thus, our specific objectives were: (1) to show how the measure can reveal which participants with diverse problem-solving styles were left behind in a set of AI products; and (2) to relate participants’ problem-solving diversity to their demographic diversity, specifically gender and age.

Methods: We performed 18 experiments, discarding two that failed manipulation checks. Each experiment was a 2x2 factorial experiment with online participants, comparing two AI products: one deliberately violating one of 18 HAI guideline and the other applying the same guideline. For our first objective, we used our measure to analyze how much each AI product gained/lost HAI-UX inclusivity compared to its counterpart, where inclusivity meant supportiveness to participants with particular problem-solving styles. For our second objective, we analyzed how participants’ problem-solving styles aligned with their gender identities and ages.

Results & Implications: Participants’ diverse problem-solving styles revealed six types of inclusivity results: (1) the AI products that followed an HAI guideline were almost always more inclusive across diversity of problem-solving styles than the products that did not follow that guideline—but “who” got most of the inclusivity varied widely by guideline and by problem-solving style; (2) when an AI product had risk implications, four variables’ values varied in tandem: participants’ feelings of control, their (lack of) suspicion, their trust in the product, and their certainty while using the product; (3) the more control an AI product offered users, the more inclusive it was; (4) whether an AI product was learning from “my” data or other people’s affected how inclusive that product was; (5) participants’ problem-solving styles skewed differently by gender and age group; and (6) almost all of the results suggested actions that HAI practitioners could take to improve their products’ inclusivity further. Together, these results suggest that a key to improving the demographic inclusivity of an AI product (e.g., across a wide range of genders, ages, etc.) can often be obtained by improving the product’s support of diverse problem-solving styles.