M.L. Tielman
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
61 records found
1
"what's on your mind?"
Understanding the Development of Multidimensional Trust in Social Robots
Conference paper
(2026)
-
Chih Wei Ning, Carolina Centeio Jorge, Myrthe L. Tielman, Mark A. Neerincx
As robots and virtual agents are increasingly envisioned as long-term companions, understanding how trust develops becomes crucial for ensuring safe and appropriate human-robot relationships. This research investigates how affective and cognitive trust evolve in social human-robot interactions. Participants (n=40) engaged in a 2 (social attitude: social, baseline) × 3 (time: t1, t2, t3) mixed-design user study with a social robot, using a novel Card Divination Task developed to elicit both cognitive and affective trust dimensions. Results show that cognitive trust develops early while affective trust emerges gradually. Moreover, social cues enhance both cognitive trust, affective trust, and participants' certainty in trust judgment. These findings provide empirical support for the theoretical distinction between trust dimensions and highlight the role of social behavior in shaping trust over repeated interactions.
...
As robots and virtual agents are increasingly envisioned as long-term companions, understanding how trust develops becomes crucial for ensuring safe and appropriate human-robot relationships. This research investigates how affective and cognitive trust evolve in social human-robot interactions. Participants (n=40) engaged in a 2 (social attitude: social, baseline) × 3 (time: t1, t2, t3) mixed-design user study with a social robot, using a novel Card Divination Task developed to elicit both cognitive and affective trust dimensions. Results show that cognitive trust develops early while affective trust emerges gradually. Moreover, social cues enhance both cognitive trust, affective trust, and participants' certainty in trust judgment. These findings provide empirical support for the theoretical distinction between trust dimensions and highlight the role of social behavior in shaping trust over repeated interactions.
Children’s helplines train new counselors to adapt to children’s needs and values. This training typically involves roleplay, which can be resource-intensive. Interactive agents offer a promising alternative; yet, simulation-based training systems rarely model how personal values influence decision-making. We present a value-integrated belief–desire–intention (BDI) model that simulates virtual children whose behavior is guided by underlying values. The trainees’ task is to apply motivational interviewing to recognize and align with the child’s values. We conducted a between-subjects experiment (N = 193) comparing three conditions: a base BDI virtual child, a BDI virtual child with integrated values, and one with both integrated values and explanatory feedback on value-based reasoning. Results showed credible support that integrating values improves participants’ opportunities to align with a virtual child and enhances their situational awareness based on a child’s values. We also found some support that feedback improved value recognition and perceived usefulness. Additionally, integrating values improved believability and overall experience. These findings suggest that the proposed values-based model enables more targeted training, which we anticipate will better prepare counselors for value-sensitive conversations.
...
Children’s helplines train new counselors to adapt to children’s needs and values. This training typically involves roleplay, which can be resource-intensive. Interactive agents offer a promising alternative; yet, simulation-based training systems rarely model how personal values influence decision-making. We present a value-integrated belief–desire–intention (BDI) model that simulates virtual children whose behavior is guided by underlying values. The trainees’ task is to apply motivational interviewing to recognize and align with the child’s values. We conducted a between-subjects experiment (N = 193) comparing three conditions: a base BDI virtual child, a BDI virtual child with integrated values, and one with both integrated values and explanatory feedback on value-based reasoning. Results showed credible support that integrating values improves participants’ opportunities to align with a virtual child and enhances their situational awareness based on a child’s values. We also found some support that feedback improved value recognition and perceived usefulness. Additionally, integrating values improved believability and overall experience. These findings suggest that the proposed values-based model enables more targeted training, which we anticipate will better prepare counselors for value-sensitive conversations.
Journal article
(2026)
-
Myrthe L. Tielman, Morgan Bailey, Francesco Frattolillo, Carolina Centeio Jorge, Anna Sophie Ulfert, André Meyer-Vitali
Human-AI teamwork is no longer a topic of the future. Given the importance of trust in human teams, the question arises how trust functions in human-AI teams. Although trust has long been studied from a human-centred perspective (e.g. in psychology and philosophy), a computational perspective and from the perspective of human trust in AI (e.g. in human-computer interaction), the study of trust in human-AI interaction in a team setting is still a novel field. For this reason, the MULTITTRUST (Multidisciplinary perspectives on Human-AI Team Trust) workshop series was founded. In this paper, we present the main outcomes after three editions. Our contributions are: an overview of the shared language of concepts and definitions; an outline of the main open research challenges; and methodological guidelines for further studies in meaningful human-AI team trust. These three contributions form a foundational roadmap towards a better understanding of trust in human-AI team interactions.
...
Human-AI teamwork is no longer a topic of the future. Given the importance of trust in human teams, the question arises how trust functions in human-AI teams. Although trust has long been studied from a human-centred perspective (e.g. in psychology and philosophy), a computational perspective and from the perspective of human trust in AI (e.g. in human-computer interaction), the study of trust in human-AI interaction in a team setting is still a novel field. For this reason, the MULTITTRUST (Multidisciplinary perspectives on Human-AI Team Trust) workshop series was founded. In this paper, we present the main outcomes after three editions. Our contributions are: an overview of the shared language of concepts and definitions; an outline of the main open research challenges; and methodological guidelines for further studies in meaningful human-AI team trust. These three contributions form a foundational roadmap towards a better understanding of trust in human-AI team interactions.
Social AI for a Healthier Lifestyle
Four Competencies to Manage and Prevent Chronic Diseases
Conference paper
(2025)
-
Mark Neerincx, Jasper van der Waa, Myrthe L. Tielman, Chenxu Hao, Liv Ziegfeld, Davide Dell’Anna, Shihan Wang
Lifestyle-related diseases like type 2 diabetes mellitus (T2DM) and chronic obstructive pulmonary disease (COPD), have a major impact on society, asking for comprehensive disease management support. While AI technology has advanced for diagnosis and disease detection, its implementation into eHealth and mHealth applications remains limited, with low adoption rates and limited evidence of effectiveness. To achieve the necessary levels of client engagement and self-efficacy in chronic disease lifestyle management (CDLM), Artificial Intelligence (AI) support must demonstrate social competencies throughout its entire lifecycle—an under-researched topic. This paper introduces a novel Social AI Competence framework designed to provide durable personalized CDLM-support. The framework defines four complementary core competencies: (1) supporting meaningful activities, (2) providing responsible actionable explanations, (3) engaging persons in reflective interactions, and (4) strengthening and leveraging support networks. Underlying these competencies are eleven key social skills, detailed in terms of their foundation, functionality, state-of-the-art advancements, and research and development challenges. The CDLM system under development employs interactive modeling techniques to incorporate the experience and expertise of both experts and clients into these skills, supported by a modular architecture that ensures adaptability and scalability. Integrating social AI functions into the competency framework enables systematic assessment and optimization of their proportional effectiveness in real-world use cases.
...
Lifestyle-related diseases like type 2 diabetes mellitus (T2DM) and chronic obstructive pulmonary disease (COPD), have a major impact on society, asking for comprehensive disease management support. While AI technology has advanced for diagnosis and disease detection, its implementation into eHealth and mHealth applications remains limited, with low adoption rates and limited evidence of effectiveness. To achieve the necessary levels of client engagement and self-efficacy in chronic disease lifestyle management (CDLM), Artificial Intelligence (AI) support must demonstrate social competencies throughout its entire lifecycle—an under-researched topic. This paper introduces a novel Social AI Competence framework designed to provide durable personalized CDLM-support. The framework defines four complementary core competencies: (1) supporting meaningful activities, (2) providing responsible actionable explanations, (3) engaging persons in reflective interactions, and (4) strengthening and leveraging support networks. Underlying these competencies are eleven key social skills, detailed in terms of their foundation, functionality, state-of-the-art advancements, and research and development challenges. The CDLM system under development employs interactive modeling techniques to incorporate the experience and expertise of both experts and clients into these skills, supported by a modular architecture that ensures adaptability and scalability. Integrating social AI functions into the competency framework enables systematic assessment and optimization of their proportional effectiveness in real-world use cases.
Journal article
(2025)
-
P.Y. Chen, M. Birna van Riemsdijk, Dirk K.J. Heylen, C.M. Jonker, M.L. Tielman
Effective support from personal assistive technologies relies on accurate user models that capture user values, preferences, and context. Knowledge-based techniques model these relationships, enabling support agents to align their actions with user values. However, understanding values in a single context is insufficient due to the dynamic nature of behaviour. This study explores the use of dialogue strategies to update user models. Participants were randomly assigned to different strategies and they discussed one randomly chosen non-adherence situation with the agent. Then, their emotions, acquired information accuracy, completeness, and dialogue experience were rated. Our findings suggest that multiple-choice dialogues may limit response depth, reducing the perceived completeness of behaviour reasons. In contrast, open-ended questions allow more detailed input but require more time and effort, potentially worsening the dialogue experience. Through inductive coding, we identified key topics, such as individual challenges, priorities, tangible outcomes, and values, essential for constructing personalised user models. We also analyzed conversation paths to improve dialogue-based user model updates in support agents. Further research is needed to refine the relationship between dialogue strategies and self-conscious emotions, considering diverse backgrounds and health goals, while enhancing dialogue design.
...
Effective support from personal assistive technologies relies on accurate user models that capture user values, preferences, and context. Knowledge-based techniques model these relationships, enabling support agents to align their actions with user values. However, understanding values in a single context is insufficient due to the dynamic nature of behaviour. This study explores the use of dialogue strategies to update user models. Participants were randomly assigned to different strategies and they discussed one randomly chosen non-adherence situation with the agent. Then, their emotions, acquired information accuracy, completeness, and dialogue experience were rated. Our findings suggest that multiple-choice dialogues may limit response depth, reducing the perceived completeness of behaviour reasons. In contrast, open-ended questions allow more detailed input but require more time and effort, potentially worsening the dialogue experience. Through inductive coding, we identified key topics, such as individual challenges, priorities, tangible outcomes, and values, essential for constructing personalised user models. We also analyzed conversation paths to improve dialogue-based user model updates in support agents. Further research is needed to refine the relationship between dialogue strategies and self-conscious emotions, considering diverse backgrounds and health goals, while enhancing dialogue design.
Advancing Human-Machine Teaming
Definitions, Challenges, Future Directions
Humans and intelligent machines increasingly collaborate on complex tasks, although significant challenges remain before machines can function as effective teammates. The human-machine teaming research community attempts to address these challenges by developing and testing methods that identify and enhance the factors essential for successful teaming. However, this community suffers from a lack of requirements for effective research, numerous methods without centralized documentation, and a disconnect between research and real-world applications. These challenges hinder progress and limit the generalizability of research outcomes. To address these issues, we argue that the human-machine teaming research community should establish a more structured and systematic approach to studying and advancing the field. This paper identifies and discusses several key research directions and actionable outputs for such an approach. These include taxonomies and guidelines to streamline research, team design patterns to describe reusable solutions, modular testbeds to facilitate comparability and reuse, and study templates to foster creativity and encourage sharing. We believe that these elements can help formulate requirements for effective human-machine teaming research and foster the development of modular and well-documented testbeds. Achieving these goals can contribute to more ecologically valid human-machine teaming research and, thus, a stronger connection between research and real-world applications.
...
Humans and intelligent machines increasingly collaborate on complex tasks, although significant challenges remain before machines can function as effective teammates. The human-machine teaming research community attempts to address these challenges by developing and testing methods that identify and enhance the factors essential for successful teaming. However, this community suffers from a lack of requirements for effective research, numerous methods without centralized documentation, and a disconnect between research and real-world applications. These challenges hinder progress and limit the generalizability of research outcomes. To address these issues, we argue that the human-machine teaming research community should establish a more structured and systematic approach to studying and advancing the field. This paper identifies and discusses several key research directions and actionable outputs for such an approach. These include taxonomies and guidelines to streamline research, team design patterns to describe reusable solutions, modular testbeds to facilitate comparability and reuse, and study templates to foster creativity and encourage sharing. We believe that these elements can help formulate requirements for effective human-machine teaming research and foster the development of modular and well-documented testbeds. Achieving these goals can contribute to more ecologically valid human-machine teaming research and, thus, a stronger connection between research and real-world applications.
Journal article
(2025)
-
C. Hao, Susanne Uusitalo, C.A. Figueroa, Quirine Smit, Michael Strange, Wen-Tseng Chang, M. I. Ribeiro, Vanita Kouomogne Nana, M.L. Tielman, Maaike H.T. de Boer
As intelligent systems become more integrated into people’s daily life, systems designed to facilitate lifestyle and behavior change for health and well-being have also become more common. Previous work has identified challenges in the development and deployment of such AI-based support for diabetes lifestyle management and shown that it is necessary to shift the design process of AI-based support systems towards a human-centered approach that can be addressed by hybrid intelligence (HI). However, this shift also means adopting a user-centric design process, which brings its own challenges in terms of stakeholder involvement, evaluation processes and ethical concerns. In this perspective paper, we aim to more comprehensively identify challenges and future research directions in the development of HI systems for behavior change from four different viewpoints: (1) challenges on an individual level, such as understanding the individual end-user’s context (2) challenges on an evaluation level, such as evaluation pipelines and identifying success criteria and (3) challenges in addressing ethical implications. We show that developing HI systems for behavior change is an interdisciplinary process that requires further collaboration and consideration from various fields.
...
As intelligent systems become more integrated into people’s daily life, systems designed to facilitate lifestyle and behavior change for health and well-being have also become more common. Previous work has identified challenges in the development and deployment of such AI-based support for diabetes lifestyle management and shown that it is necessary to shift the design process of AI-based support systems towards a human-centered approach that can be addressed by hybrid intelligence (HI). However, this shift also means adopting a user-centric design process, which brings its own challenges in terms of stakeholder involvement, evaluation processes and ethical concerns. In this perspective paper, we aim to more comprehensively identify challenges and future research directions in the development of HI systems for behavior change from four different viewpoints: (1) challenges on an individual level, such as understanding the individual end-user’s context (2) challenges on an evaluation level, such as evaluation pipelines and identifying success criteria and (3) challenges in addressing ethical implications. We show that developing HI systems for behavior change is an interdisciplinary process that requires further collaboration and consideration from various fields.
Conference paper
(2025)
-
Carolina Centeio Jorge, Elena Dumitrescu, Catholijn M. Jonker, Razvan Loghin, Sahar Marossi, Elena Uleia, Myrthe L. Tielman
Mutual trust between humans and interactive artificial agents is crucial for effective human-agent teamwork. This involves not only the human appropriately trusting the artificial teammate, but also the artificial teammate assessing the human’s trustworthiness for different tasks (i.e., artificial trust in human partners). Literature indicated that transparency and explainability is generally beneficial for human-agent collaboration. However, communicating artificial trust potentially affects human trust and satisfaction, which impact team dynamics. Towards studying these effects, we developed an artificial trust model and implemented five distinct communication approaches which varied in modality (visual/graphical and/or text), level (communication and/or explanation), and timing (real-time or occasional). We evaluated the effects of the different communication styles through a user study (N=120) in a 2D grid-world Search and Rescue scenario. Our results show that all our artificial trust explanations improved human trust and satisfaction, but the mere graphical communication of it did not. These results are bound to the specific scenario and context in which this study was run and require further exploration. As such, this work presents a first step towards understanding the consequences of communicating and explaining to a human teammate their assessed trustworthiness.
...
Mutual trust between humans and interactive artificial agents is crucial for effective human-agent teamwork. This involves not only the human appropriately trusting the artificial teammate, but also the artificial teammate assessing the human’s trustworthiness for different tasks (i.e., artificial trust in human partners). Literature indicated that transparency and explainability is generally beneficial for human-agent collaboration. However, communicating artificial trust potentially affects human trust and satisfaction, which impact team dynamics. Towards studying these effects, we developed an artificial trust model and implemented five distinct communication approaches which varied in modality (visual/graphical and/or text), level (communication and/or explanation), and timing (real-time or occasional). We evaluated the effects of the different communication styles through a user study (N=120) in a 2D grid-world Search and Rescue scenario. Our results show that all our artificial trust explanations improved human trust and satisfaction, but the mere graphical communication of it did not. These results are bound to the specific scenario and context in which this study was run and require further exploration. As such, this work presents a first step towards understanding the consequences of communicating and explaining to a human teammate their assessed trustworthiness.
Agent Allocation of Moral Decisions in Human-Agent Teams
Raise Human Involvement and Explain Potential Consequences
Humans and artificial intelligence agents increasingly collaborate in morally sensitive situations such as firefighting. These agents can often perform tasks with minimal human control, challenging accountability and responsibility. Combining higher agent autonomy levels with meaningful human control can address such challenges. For example, agents can allocate decisions to themselves in less morally sensitive situations and to humans in more sensitive ones. However, how to responsibly and effectively design and implement agents for this dynamic task allocation remains unclear, with their autonomy level and provided explanations being crucial considerations. Therefore, we conducted experiments in simulated firefighting environments where participants (n = 72) collaborated with a more and less autonomous artificial moral agent. These agents provided no additional information, feature contributions, or potential consequences when allocating decision-making. Our results show that moral trust, agreement, and meaningful human control are higher when the agent is less autonomous. Furthermore, people disagree and reallocate decisions to themselves more when the agents explain potential consequences, especially when moral sensitivity is higher. Overall, our findings highlight that people prefer more involvement over higher agent autonomy and take on greater moral responsibility when agents explain potential consequences. These actionable insights are crucial for designing transparent artificial moral agents that enhance human moral awareness and responsibility. Ultimately, this supports the responsible implementation of dynamic task allocation in practice and enhances human-agent collaboration in morally sensitive situations.
...
Humans and artificial intelligence agents increasingly collaborate in morally sensitive situations such as firefighting. These agents can often perform tasks with minimal human control, challenging accountability and responsibility. Combining higher agent autonomy levels with meaningful human control can address such challenges. For example, agents can allocate decisions to themselves in less morally sensitive situations and to humans in more sensitive ones. However, how to responsibly and effectively design and implement agents for this dynamic task allocation remains unclear, with their autonomy level and provided explanations being crucial considerations. Therefore, we conducted experiments in simulated firefighting environments where participants (n = 72) collaborated with a more and less autonomous artificial moral agent. These agents provided no additional information, feature contributions, or potential consequences when allocating decision-making. Our results show that moral trust, agreement, and meaningful human control are higher when the agent is less autonomous. Furthermore, people disagree and reallocate decisions to themselves more when the agents explain potential consequences, especially when moral sensitivity is higher. Overall, our findings highlight that people prefer more involvement over higher agent autonomy and take on greater moral responsibility when agents explain potential consequences. These actionable insights are crucial for designing transparent artificial moral agents that enhance human moral awareness and responsibility. Ultimately, this supports the responsible implementation of dynamic task allocation in practice and enhances human-agent collaboration in morally sensitive situations.
"even explanations will not help in trusting [this] fundamentally biased system"
A Predictive Policing Case-Study
Conference paper
(2025)
-
Siddharth Mehrotra, Ujwal Gadiraju, Eva Bittner, Folkert Van Delden, Catholijn M. Jonker, Myrthe L. Tielman
In today's society, where Artificial Intelligence (AI) has gained a vital role, concerns regarding user's trust have garnered significant attention. The use of AI systems in high-risk domains have often led users to either under-trust it, potentially causing inadequate reliance or over-trust it, resulting in over-compliance. Therefore, users must maintain an appropriate level of trust. Past research has indicated that explanations provided by AI systems can enhance user understanding of when to trust or not trust the system. However, the utility of presentation of different explanations forms still remains to be explored especially in high-risk domains. Therefore, this study explores the impact of different explanation types (text, visual, and hybrid) and user expertise (retired police officers and lay users) on establishing appropriate trust in AI-based predictive policing. While we observed that the hybrid form of explanations increased the subjective trust in AI for expert users, it did not led to better decision-making. Furthermore, no form of explanations helped build appropriate trust. The findings of our study emphasize the importance of re-evaluating the use of explanations to build [appropriate] trust in AI based systems especially when the system's use is questionable. Finally, we synthesize potential challenges and policy recommendations based on our results to design for appropriate trust in high-risk based AI-based systems.
...
In today's society, where Artificial Intelligence (AI) has gained a vital role, concerns regarding user's trust have garnered significant attention. The use of AI systems in high-risk domains have often led users to either under-trust it, potentially causing inadequate reliance or over-trust it, resulting in over-compliance. Therefore, users must maintain an appropriate level of trust. Past research has indicated that explanations provided by AI systems can enhance user understanding of when to trust or not trust the system. However, the utility of presentation of different explanations forms still remains to be explored especially in high-risk domains. Therefore, this study explores the impact of different explanation types (text, visual, and hybrid) and user expertise (retired police officers and lay users) on establishing appropriate trust in AI-based predictive policing. While we observed that the hybrid form of explanations increased the subjective trust in AI for expert users, it did not led to better decision-making. Furthermore, no form of explanations helped build appropriate trust. The findings of our study emphasize the importance of re-evaluating the use of explanations to build [appropriate] trust in AI based systems especially when the system's use is questionable. Finally, we synthesize potential challenges and policy recommendations based on our results to design for appropriate trust in high-risk based AI-based systems.
Book chapter
(2024)
-
Carolina Centeio Jorge, Emma van Zoelen, Ruben Verhagen, Siddharth Mehrotra, Catholijn M. Jonker, Myrthe Tielman
As human-machine teams become a more common scenario, we need to ensure mutual trust between humans and machines. More important than having trust, we need all teammates to trust each other appropriately. This means that they should not overtrust or undertrust each other, avoiding risks and inefficiencies, respectively. We usually think of natural trust, that is, humans trusting machines, but we should also consider artificial trust, that is, artificial agents trusting humans. Appropriate artificial trust allows the agents to interpret human behavior and predict their behavior in a certain context. In this chapter, we explore how we can define this context in terms of task and team characteristics. We present a taxonomy that shows how trust is context-dependent. In fact, we propose that no trust model presented in the literature fits all contexts and argue that our taxonomy facilitates the choice of the trust model that better fits a certain context. The taxonomy helps to understand which internal characteristics of the teammate (krypta) are important to consider and how they will show in behavior cues (manifesta). This taxonomy can also be used to help human-machine teams’ researchers in the problem definition and process of experimental design as it allows a detailed characterization of the task and team configuration. Furthermore, we propose a formalization of the belief of trust as context-dependent trustworthiness, and show how beliefs of trust can be used to reach appropriate trust. Our work provides a starting point to implement mutual appropriate trust in human-machine teams.
...
As human-machine teams become a more common scenario, we need to ensure mutual trust between humans and machines. More important than having trust, we need all teammates to trust each other appropriately. This means that they should not overtrust or undertrust each other, avoiding risks and inefficiencies, respectively. We usually think of natural trust, that is, humans trusting machines, but we should also consider artificial trust, that is, artificial agents trusting humans. Appropriate artificial trust allows the agents to interpret human behavior and predict their behavior in a certain context. In this chapter, we explore how we can define this context in terms of task and team characteristics. We present a taxonomy that shows how trust is context-dependent. In fact, we propose that no trust model presented in the literature fits all contexts and argue that our taxonomy facilitates the choice of the trust model that better fits a certain context. The taxonomy helps to understand which internal characteristics of the teammate (krypta) are important to consider and how they will show in behavior cues (manifesta). This taxonomy can also be used to help human-machine teams’ researchers in the problem definition and process of experimental design as it allows a detailed characterization of the task and team configuration. Furthermore, we propose a formalization of the belief of trust as context-dependent trustworthiness, and show how beliefs of trust can be used to reach appropriate trust. Our work provides a starting point to implement mutual appropriate trust in human-machine teams.
Journal article
(2024)
-
Siddharth Mehrotra, Carolina Centeio Jorge, Catholijn M. Jonker, Myrthe L. Tielman
Appropriate trust is an important component of the interaction between people and AI systems, in that "inappropriate"trust can cause disuse, misuse, or abuse of AI. To foster appropriate trust in AI, we need to understand how AI systems can elicit appropriate levels of trust from their users. Out of the aspects that influence trust, this article focuses on the effect of showing integrity. In particular, this article presents a study of how different integrity-based explanations made by an AI agent affect the appropriateness of trust of a human in that agent. To explore this, (1) we provide a formal definition to measure appropriate trust, (2) present a between-subject user study with 160 participants who collaborated with an AI agent in such a task. In the study, the AI agent assisted its human partner in estimating calories on a food plate by expressing its integrity through explanations focusing on either honesty, transparency, or fairness. Our results show that (a) an agent who displays its integrity by being explicit about potential biases in data or algorithms achieved appropriate trust more often compared to being honest about capability or transparent about the decision-making process, and (b) subjective trust builds up and recovers better with honesty-like integrity explanations. Our results contribute to the design of agent-based AI systems that guide humans to appropriately trust them, a formal method to measure appropriate trust, and how to support humans in calibrating their trust in AI.
...
Appropriate trust is an important component of the interaction between people and AI systems, in that "inappropriate"trust can cause disuse, misuse, or abuse of AI. To foster appropriate trust in AI, we need to understand how AI systems can elicit appropriate levels of trust from their users. Out of the aspects that influence trust, this article focuses on the effect of showing integrity. In particular, this article presents a study of how different integrity-based explanations made by an AI agent affect the appropriateness of trust of a human in that agent. To explore this, (1) we provide a formal definition to measure appropriate trust, (2) present a between-subject user study with 160 participants who collaborated with an AI agent in such a task. In the study, the AI agent assisted its human partner in estimating calories on a food plate by expressing its integrity through explanations focusing on either honesty, transparency, or fairness. Our results show that (a) an agent who displays its integrity by being explicit about potential biases in data or algorithms achieved appropriate trust more often compared to being honest about capability or transparent about the decision-making process, and (b) subjective trust builds up and recovers better with honesty-like integrity explanations. Our results contribute to the design of agent-based AI systems that guide humans to appropriately trust them, a formal method to measure appropriate trust, and how to support humans in calibrating their trust in AI.
In human-machine teams, the strengths and weaknesses of both team members result in dependencies, opportunities, and requirements to collaborate. Managing these interdependence relationships is crucial for teamwork, as it is argued that they facilitate accurate trust calibration. Unfortunately, empirical research on the influence of interdependence on trust calibration during human-machine teamwork is lacking. Therefore, we conducted an experiment (n=80) to study the effect of interdependence relationships (complete independence, complementary independence, optional interdependence, required interdependence) on human-machine trust calibration. Participants collaborated with a virtual agent during a simulated search and rescue task in teams characterized by one of the four interdependencies. A machine-induced trust violation was included in the task to facilitate dynamic trust calibration. Results show that the interdependence relationships during human-machine teamwork influence perceived trust calibration over time. Only in the teams with joint actions (optional and required interdependence) does perceived trust in the machine not recover to its initial pre-violated value. However, results show that the correlation between perceived trust in the machine and machine trustworthiness is strongest in these teams with joint actions, suggesting a more accurate trust calibration process. Overall, our findings provide some first evidence that interdependence relationships during human-machine teamwork influence human-machine trust calibration.
...
In human-machine teams, the strengths and weaknesses of both team members result in dependencies, opportunities, and requirements to collaborate. Managing these interdependence relationships is crucial for teamwork, as it is argued that they facilitate accurate trust calibration. Unfortunately, empirical research on the influence of interdependence on trust calibration during human-machine teamwork is lacking. Therefore, we conducted an experiment (n=80) to study the effect of interdependence relationships (complete independence, complementary independence, optional interdependence, required interdependence) on human-machine trust calibration. Participants collaborated with a virtual agent during a simulated search and rescue task in teams characterized by one of the four interdependencies. A machine-induced trust violation was included in the task to facilitate dynamic trust calibration. Results show that the interdependence relationships during human-machine teamwork influence perceived trust calibration over time. Only in the teams with joint actions (optional and required interdependence) does perceived trust in the machine not recover to its initial pre-violated value. However, results show that the correlation between perceived trust in the machine and machine trustworthiness is strongest in these teams with joint actions, suggesting a more accurate trust calibration process. Overall, our findings provide some first evidence that interdependence relationships during human-machine teamwork influence human-machine trust calibration.
Appropriate Trust in Artificial Intelligence (AI) systems has rapidly become an important area of focus for both researchers and practitioners. Various approaches have been used to achieve it, such as confidence scores, explanations, trustworthiness cues, or uncertainty communication. However, a comprehensive understanding of the field is lacking due to the diversity of perspectives arising from various backgrounds that influence it and the lack of a single definition for appropriate trust. To investigate this topic, this paper presents a systematic review to identify current practices in building appropriate trust, different ways to measure it, types of tasks used, and potential challenges associated with it. We also propose a Belief, Intentions, and Actions (BIA) mapping to study commonalities and differences in the concepts related to appropriate trust by (a) describing the existing disagreements on defining appropriate trust, and (b) providing an overview of the concepts and definitions related to appropriate trust in AI from the existing literature. Finally, the challenges identified in studying appropriate trust are discussed, and observations are summarized as current trends, potential gaps, and research opportunities for future work. Overall, the paper provides insights into the complex concept of appropriate trust in human-AI interaction and presents research opportunities to advance our understanding on this topic.
...
Appropriate Trust in Artificial Intelligence (AI) systems has rapidly become an important area of focus for both researchers and practitioners. Various approaches have been used to achieve it, such as confidence scores, explanations, trustworthiness cues, or uncertainty communication. However, a comprehensive understanding of the field is lacking due to the diversity of perspectives arising from various backgrounds that influence it and the lack of a single definition for appropriate trust. To investigate this topic, this paper presents a systematic review to identify current practices in building appropriate trust, different ways to measure it, types of tasks used, and potential challenges associated with it. We also propose a Belief, Intentions, and Actions (BIA) mapping to study commonalities and differences in the concepts related to appropriate trust by (a) describing the existing disagreements on defining appropriate trust, and (b) providing an overview of the concepts and definitions related to appropriate trust in AI from the existing literature. Finally, the challenges identified in studying appropriate trust are discussed, and observations are summarized as current trends, potential gaps, and research opportunities for future work. Overall, the paper provides insights into the complex concept of appropriate trust in human-AI interaction and presents research opportunities to advance our understanding on this topic.
Agent-based training systems can enhance people's social skills. The effective development of these systems needs a comprehensive architecture that outlines their components and relationships. Such an architecture can pinpoint improvement areas and future outlooks. This paper presents ARTES: a general architecture illustrating how components of agent-based social training systems work together. We studied existing systems and architectures for training and tutoring to design ARTES and identify its essential components and interaction characteristics. ARTES comprises two core components: the agent simulation of social situations, and educational elements to provide guided learning. We link ARTES's crucial components to four primary learning theories (behaviourism, cognitivism, social cognitive theory, and constructivism) to illustrate the role of agent simulation and tutoring elements in establishing desired learning outcomes. Furthermore, we map ARTES's components against eight architectures, 43 systems and three tools to indicate the components' relevance, completeness, generalisation, and deployment potential across contexts. In addition to ARTES, the paper also contributes by identifying future improvements and research directions, such as the agent's thinking, tutoring methods, knowledge transfer, and ethical implications. We believe ARTES can help bridge the gap between virtual human simulations and impactful educational learning, offering training system developers desirable features like understandability and adaptability.
...
Agent-based training systems can enhance people's social skills. The effective development of these systems needs a comprehensive architecture that outlines their components and relationships. Such an architecture can pinpoint improvement areas and future outlooks. This paper presents ARTES: a general architecture illustrating how components of agent-based social training systems work together. We studied existing systems and architectures for training and tutoring to design ARTES and identify its essential components and interaction characteristics. ARTES comprises two core components: the agent simulation of social situations, and educational elements to provide guided learning. We link ARTES's crucial components to four primary learning theories (behaviourism, cognitivism, social cognitive theory, and constructivism) to illustrate the role of agent simulation and tutoring elements in establishing desired learning outcomes. Furthermore, we map ARTES's components against eight architectures, 43 systems and three tools to indicate the components' relevance, completeness, generalisation, and deployment potential across contexts. In addition to ARTES, the paper also contributes by identifying future improvements and research directions, such as the agent's thinking, tutoring methods, knowledge transfer, and ethical implications. We believe ARTES can help bridge the gap between virtual human simulations and impactful educational learning, offering training system developers desirable features like understandability and adaptability.
Child helplines offer a safe and private space for children to share their thoughts and feelings with volunteers. However, training these volunteers to help can be both expensive and time-consuming. In this demo, we present Lilobot, a conversational agent designed to train volunteers for child helplines. Lilobot’s reasoning is based on the Belief-Desire-Intention (BDI) model, which simulates, for example, a bullied child who contacts the helpline through text. Users engage with Lilobot in a role-play format, taking on the volunteer’s role. Through this system, volunteers can practice applying the Five Phase Model, a conversational strategy helplines use. The training tool includes a trainer interface for monitoring and modifying Lilobot’s interactions. Trainers can also create new conversational scenarios through an authoring tool. An initial evaluation led to enhancements in Lilobot’s knowledge base and intent recognition, addressing the main issues encountered by participants. The components used to implement the system were Java Spring for the BDI model and the authoring tool, Rasa for Natural Language Understanding, PostgreSQL for the database, and Vue.js for the front-end. This tool aims to provide volunteers with consistent, interactive training, enhancing their counselling skills in a controlled environment.
...
Child helplines offer a safe and private space for children to share their thoughts and feelings with volunteers. However, training these volunteers to help can be both expensive and time-consuming. In this demo, we present Lilobot, a conversational agent designed to train volunteers for child helplines. Lilobot’s reasoning is based on the Belief-Desire-Intention (BDI) model, which simulates, for example, a bullied child who contacts the helpline through text. Users engage with Lilobot in a role-play format, taking on the volunteer’s role. Through this system, volunteers can practice applying the Five Phase Model, a conversational strategy helplines use. The training tool includes a trainer interface for monitoring and modifying Lilobot’s interactions. Trainers can also create new conversational scenarios through an authoring tool. An initial evaluation led to enhancements in Lilobot’s knowledge base and intent recognition, addressing the main issues encountered by participants. The components used to implement the system were Java Spring for the BDI model and the authoring tool, Rasa for Natural Language Understanding, PostgreSQL for the database, and Vue.js for the front-end. This tool aims to provide volunteers with consistent, interactive training, enhancing their counselling skills in a controlled environment.
Conference paper
(2024)
-
Chadha Degachi, Siddharth Mehrotra, Mireia Yurrita, Evangelos Niforatos, Myrthe Tielman
Appropriate trust, trust which aligns with system trustworthiness, in Artificial Intelligence (AI) systems has become an important area of research. However, there remains debate in the community about how to design for appropriate trust. This debate is a result of the complex nature of trust in AI, which can be difficult to understand and evaluate, as well as the lack of holistic approaches to trust. In this paper, we aim to clarify some of this debate by operationalising appropriate trust within the context of the Human-Centred AI Design (HCD) process. To do so, we organised three workshops with 13 participants total from design and development backgrounds. We carried out design activities to stimulate discussion on appropriate trust in the HCD process. This paper aims to help researchers and practitioners understand appropriate trust in AI through a design lens by illustrating how it interacts with the HCD process.
...
Appropriate trust, trust which aligns with system trustworthiness, in Artificial Intelligence (AI) systems has become an important area of research. However, there remains debate in the community about how to design for appropriate trust. This debate is a result of the complex nature of trust in AI, which can be difficult to understand and evaluate, as well as the lack of holistic approaches to trust. In this paper, we aim to clarify some of this debate by operationalising appropriate trust within the context of the Human-Centred AI Design (HCD) process. To do so, we organised three workshops with 13 participants total from design and development backgrounds. We carried out design activities to stimulate discussion on appropriate trust in the HCD process. This paper aims to help researchers and practitioners understand appropriate trust in AI through a design lens by illustrating how it interacts with the HCD process.
In teams composed of humans, we use trust in others to make decisions, such as what to do next, who to help and who to ask for help. When a team member is artificial, they should also be able to assess whether a human teammate is trustworthy for a certain task. We see trustworthiness as the combination of (1) whether someone will do a task and (2) whether they can do it. With building beliefs in trustworthiness as an ultimate goal, we explore which internal factors (krypta) of the human may play a role (e.g., ability, benevolence, and integrity) in determining trustworthiness, according to existing literature. Furthermore, we investigate which observable metrics (manifesta) an agent may take into account as cues for the human teammate’s krypta in an online 2D grid-world experiment (n = 54). Results suggest that cues of ability, benevolence and integrity influence trustworthiness. However, we observed that trustworthiness is mainly influenced by human’s playing strategy and cost-benefit analysis, which deserves further investigation. This is a first step towards building informed beliefs of human trustworthiness in human-AI teamwork.
...
In teams composed of humans, we use trust in others to make decisions, such as what to do next, who to help and who to ask for help. When a team member is artificial, they should also be able to assess whether a human teammate is trustworthy for a certain task. We see trustworthiness as the combination of (1) whether someone will do a task and (2) whether they can do it. With building beliefs in trustworthiness as an ultimate goal, we explore which internal factors (krypta) of the human may play a role (e.g., ability, benevolence, and integrity) in determining trustworthiness, according to existing literature. Furthermore, we investigate which observable metrics (manifesta) an agent may take into account as cues for the human teammate’s krypta in an online 2D grid-world experiment (n = 54). Results suggest that cues of ability, benevolence and integrity influence trustworthiness. However, we observed that trustworthiness is mainly influenced by human’s playing strategy and cost-benefit analysis, which deserves further investigation. This is a first step towards building informed beliefs of human trustworthiness in human-AI teamwork.