Carolina Centeio Jorge, Catholijn M. Jonker, Myrthe L. Tielman
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.
{"title":"How should an AI trust its human teammates? Exploring possible cues of artificial trust","authors":"Carolina Centeio Jorge, Catholijn M. Jonker, Myrthe L. Tielman","doi":"10.1145/3635475","DOIUrl":"https://doi.org/10.1145/3635475","url":null,"abstract":"<p>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.</p>","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2023-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138545567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rui Zhang, Christopher Flathmann, Geoff Musick, Beau Schelble, Nathan J. McNeese, Bart Knijnenburg, Wen Duan
Explanation of artificial intelligence (AI) decision-making has become an important research area in human-computer interaction (HCI) and computer-supported teamwork research. While plenty of research has investigated AI explanations with an intent to improve AI transparency and human trust in AI, how AI explanations function in teaming environments remains unclear. Given that a major benefit of AI giving explanations is to increase human trust understanding how AI explanations impact human trust is crucial to effective human-AI teamwork. An online experiment was conducted with 156 participants to explore this question by examining how a teammate’s explanations impact the perceived trust of the teammate and the effectiveness of the team and how these impacts vary based on whether the teammate is a human or an AI. This study shows that explanations facilitate trust in AI teammates when explaining why AI disobeyed humans’ orders but hindered trust when explaining why an AI lied to humans. In addition, participants’ personal characteristics (e.g., their gender and the individual’s ethical framework) impacted their perceptions of AI teammates both directly and indirectly in different scenarios. Our study contributes to interactive intelligent systems and HCI by shedding light on how an AI teammate’s actions and corresponding explanations are perceived by humans while identifying factors that impact trust and perceived effectiveness. This work provides an initial understanding of AI explanations in human-AI teams, which can be used for future research to build upon in exploring AI explanation implementation in collaborative environments.
{"title":"I Know This Looks Bad, But I Can Explain: Understanding When AI Should Explain Actions In Human-AI Teams","authors":"Rui Zhang, Christopher Flathmann, Geoff Musick, Beau Schelble, Nathan J. McNeese, Bart Knijnenburg, Wen Duan","doi":"10.1145/3635474","DOIUrl":"https://doi.org/10.1145/3635474","url":null,"abstract":"<p>Explanation of artificial intelligence (AI) decision-making has become an important research area in human-computer interaction (HCI) and computer-supported teamwork research. While plenty of research has investigated AI explanations with an intent to improve AI transparency and human trust in AI, how AI explanations function in teaming environments remains unclear. Given that a major benefit of AI giving explanations is to increase human trust understanding how AI explanations impact human trust is crucial to effective human-AI teamwork. An online experiment was conducted with 156 participants to explore this question by examining how a teammate’s explanations impact the perceived trust of the teammate and the effectiveness of the team and how these impacts vary based on whether the teammate is a human or an AI. This study shows that explanations facilitate trust in AI teammates when explaining why AI disobeyed humans’ orders but hindered trust when explaining why an AI lied to humans. In addition, participants’ personal characteristics (e.g., their gender and the individual’s ethical framework) impacted their perceptions of AI teammates both directly and indirectly in different scenarios. Our study contributes to interactive intelligent systems and HCI by shedding light on how an AI teammate’s actions and corresponding explanations are perceived by humans while identifying factors that impact trust and perceived effectiveness. This work provides an initial understanding of AI explanations in human-AI teams, which can be used for future research to build upon in exploring AI explanation implementation in collaborative environments.</p>","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2023-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138508056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Whereas most research in AI system explanation for healthcare applications looks at developing algorithmic explanations targeted at AI experts or medical professionals, the question we raise is: How do we build meaningful explanations for laypeople? And how does a meaningful explanation affect user’s trust perceptions? Our research investigates how the key factors affecting human-AI trust change in the light of human expertise, and how to design explanations specifically targeted at non-experts. By means of a stage-based design method, we map the ways laypeople understand AI explanations in a User Explanation Model. We also map both medical professionals and AI experts’ practice in an Expert Explanation Model. A Target Explanation Model is then proposed, which represents how experts’ practice and layperson’s understanding can be combined to design meaningful explanations. Design guidelines for meaningful AI explanations are proposed, and a prototype of AI system explanation for non-expert users in a breast cancer scenario is presented and assessed on how it affect users’ trust perceptions.
{"title":"Meaningful Explanation Effect on User’s Trust in an AI Medical System: Designing Explanations for Non-Expert Users","authors":"Retno Larasati, Anna De Liddo, Enrico Motta","doi":"10.1145/3631614","DOIUrl":"https://doi.org/10.1145/3631614","url":null,"abstract":"Whereas most research in AI system explanation for healthcare applications looks at developing algorithmic explanations targeted at AI experts or medical professionals, the question we raise is: How do we build meaningful explanations for laypeople? And how does a meaningful explanation affect user’s trust perceptions? Our research investigates how the key factors affecting human-AI trust change in the light of human expertise, and how to design explanations specifically targeted at non-experts. By means of a stage-based design method, we map the ways laypeople understand AI explanations in a User Explanation Model. We also map both medical professionals and AI experts’ practice in an Expert Explanation Model. A Target Explanation Model is then proposed, which represents how experts’ practice and layperson’s understanding can be combined to design meaningful explanations. Design guidelines for meaningful AI explanations are proposed, and a prototype of AI system explanation for non-expert users in a breast cancer scenario is presented and assessed on how it affect users’ trust perceptions.","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135390620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chiradeep Roy, Mahsan Nourani, Shivvrat Arya, Mahesh Shanbhag, Tahrima Rahman, Eric D. Ragan, Nicholas Ruozzi, Vibhav Gogate
We consider the following video activity recognition (VAR) task: given a video, infer the set of activities being performed in the video and assign each frame to an activity. Although VAR can be solved accurately using existing deep learning techniques, deep networks are neither interpretable nor explainable and as a result their use is problematic in high stakes decision-making applications (e.g., in healthcare, experimental Biology, aviation, law, etc.). In such applications, failure may lead to disastrous consequences and therefore it is necessary that the user is able to either understand the inner workings of the model or probe it to understand its reasoning patterns for a given decision. We address these limitations of deep networks by proposing a new approach that feeds the output of a deep model into a tractable, interpretable probabilistic model called a dynamic conditional cutset network that is defined over the explanatory and output variables and then performing joint inference over the combined model. The two key benefits of using cutset networks are: (a) they explicitly model the relationship between the output and explanatory variables and as a result the combined model is likely to be more accurate than the vanilla deep model and (b) they can answer reasoning queries in polynomial time and as a result they can derive meaningful explanations by efficiently answering explanation queries. We demonstrate the efficacy of our approach on two datasets, Textually Annotated Cooking Scenes (TACoS), and wet lab, using conventional evaluation measures such as the Jaccard Index and Hamming Loss, as well as a human-subjects study.
{"title":"Explainable Activity Recognition in Videos using Deep Learning and Tractable Probabilistic Models","authors":"Chiradeep Roy, Mahsan Nourani, Shivvrat Arya, Mahesh Shanbhag, Tahrima Rahman, Eric D. Ragan, Nicholas Ruozzi, Vibhav Gogate","doi":"10.1145/3626961","DOIUrl":"https://doi.org/10.1145/3626961","url":null,"abstract":"We consider the following video activity recognition (VAR) task: given a video, infer the set of activities being performed in the video and assign each frame to an activity. Although VAR can be solved accurately using existing deep learning techniques, deep networks are neither interpretable nor explainable and as a result their use is problematic in high stakes decision-making applications (e.g., in healthcare, experimental Biology, aviation, law, etc.). In such applications, failure may lead to disastrous consequences and therefore it is necessary that the user is able to either understand the inner workings of the model or probe it to understand its reasoning patterns for a given decision. We address these limitations of deep networks by proposing a new approach that feeds the output of a deep model into a tractable, interpretable probabilistic model called a dynamic conditional cutset network that is defined over the explanatory and output variables and then performing joint inference over the combined model. The two key benefits of using cutset networks are: (a) they explicitly model the relationship between the output and explanatory variables and as a result the combined model is likely to be more accurate than the vanilla deep model and (b) they can answer reasoning queries in polynomial time and as a result they can derive meaningful explanations by efficiently answering explanation queries. We demonstrate the efficacy of our approach on two datasets, Textually Annotated Cooking Scenes (TACoS), and wet lab, using conventional evaluation measures such as the Jaccard Index and Hamming Loss, as well as a human-subjects study.","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136012607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marc-André Zöller, Waldemar Titov, Thomas Schlegel, Marco F. Huber
In the last ten years, various automated machine learning (AutoML) systems have been proposed to build end-to-end machine learning (ML) pipelines with minimal human interaction. Even though such automatically synthesized ML pipelines are able to achieve competitive performance, recent studies have shown that users do not trust models constructed by AutoML due to missing transparency of AutoML systems and missing explanations for the constructed ML pipelines. In a requirements analysis study with 36 domain experts, data scientists, and AutoML researchers from different professions with vastly different expertise in ML, we collect detailed informational needs for AutoML. We propose XAutoML, an interactive visual analytics tool for explaining arbitrary AutoML optimization procedures and ML pipelines constructed by AutoML. XAutoML combines interactive visualizations with established techniques from explainable artificial intelligence (XAI) to make the complete AutoML procedure transparent and explainable. By integrating XAutoML with JupyterLab, experienced users can extend the visual analytics with ad-hoc visualizations based on information extracted from XAutoML. We validate our approach in a user study with the same diverse user group from the requirements analysis. All participants were able to extract useful information from XAutoML, leading to a significantly increased understanding of ML pipelines produced by AutoML and the AutoML optimization itself.
{"title":"XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learning","authors":"Marc-André Zöller, Waldemar Titov, Thomas Schlegel, Marco F. Huber","doi":"10.1145/3625240","DOIUrl":"https://doi.org/10.1145/3625240","url":null,"abstract":"In the last ten years, various automated machine learning (AutoML) systems have been proposed to build end-to-end machine learning (ML) pipelines with minimal human interaction. Even though such automatically synthesized ML pipelines are able to achieve competitive performance, recent studies have shown that users do not trust models constructed by AutoML due to missing transparency of AutoML systems and missing explanations for the constructed ML pipelines. In a requirements analysis study with 36 domain experts, data scientists, and AutoML researchers from different professions with vastly different expertise in ML, we collect detailed informational needs for AutoML. We propose XAutoML, an interactive visual analytics tool for explaining arbitrary AutoML optimization procedures and ML pipelines constructed by AutoML. XAutoML combines interactive visualizations with established techniques from explainable artificial intelligence (XAI) to make the complete AutoML procedure transparent and explainable. By integrating XAutoML with JupyterLab, experienced users can extend the visual analytics with ad-hoc visualizations based on information extracted from XAutoML. We validate our approach in a user study with the same diverse user group from the requirements analysis. All participants were able to extract useful information from XAutoML, leading to a significantly increased understanding of ML pipelines produced by AutoML and the AutoML optimization itself.","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135343679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The IEEE TRANSACTIONS ON SIGNAL PROCESSING is fortunate to attract submissions of the highest quality and to publish articles that deal with topics that are at the forefront of what is happening in the field of signal processing and its adjacent areas. ...
IEEE TRANSACTIONS ON SIGNAL PROCESSING很幸运地吸引了最高质量的投稿，并发表了涉及信号处理领域及其邻近领域中正在发生的前沿主题的文章. ...
{"title":"2022 TiiS Best Paper Announcement","authors":"Michelle Zhou, Shlomo Berkovsky","doi":"10.1145/3615590","DOIUrl":"https://doi.org/10.1145/3615590","url":null,"abstract":"The IEEE TRANSACTIONS ON SIGNAL PROCESSING is fortunate to attract submissions of the highest quality and to publish articles that deal with topics that are at the forefront of what is happening in the field of signal processing and its adjacent areas. ...","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135980610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
While Human Activity Recognition systems may benefit from Active Learning by allowing users to self-annotate their Activities of Daily Living (ADLs), many proposed methods for collecting such annotations are for short-term data collection campaigns for specific datasets. We present a reusable dialogue-based approach to user interaction for active learning in activity recognition systems, which utilises semantic similarity measures and a dataset of natural language descriptions of common activities (which we make publicly available). Our approach involves system-initiated dialogue, including follow-up questions to reduce ambiguity in user responses where appropriate. We apply this approach to two active learning scenarios: (i) using an existing CASAS dataset, demonstrating long-term usage; and (ii) using an online activity recognition system, which tackles the issue of online segmentation and labelling. We demonstrate our work in context, in which a natural language interface provides knowledge that can help interpret other multi-modal sensor data. We provide results highlighting the potential of our dialogue- and semantic similarity-based approach. We evaluate our work: (i) quantitatively, as an efficient way to seek users’ input for active learning of ADLs; and (ii) qualitatively, through a user study in which users were asked to compare our approach and an established method. Results show the potential of our approach as a hands-free interface for annotation of sensor data as part of an active learning system. We provide insights into the challenges of active learning for activity recognition under real-world conditions and identify potential ways to address them.
{"title":"Generalisable Dialogue-based Approach for Active Learning of Activities of Daily Living","authors":"Ronnie Smith, M. Dragone","doi":"10.1145/3616017","DOIUrl":"https://doi.org/10.1145/3616017","url":null,"abstract":"While Human Activity Recognition systems may benefit from Active Learning by allowing users to self-annotate their Activities of Daily Living (ADLs), many proposed methods for collecting such annotations are for short-term data collection campaigns for specific datasets. We present a reusable dialogue-based approach to user interaction for active learning in activity recognition systems, which utilises semantic similarity measures and a dataset of natural language descriptions of common activities (which we make publicly available). Our approach involves system-initiated dialogue, including follow-up questions to reduce ambiguity in user responses where appropriate. We apply this approach to two active learning scenarios: (i) using an existing CASAS dataset, demonstrating long-term usage; and (ii) using an online activity recognition system, which tackles the issue of online segmentation and labelling. We demonstrate our work in context, in which a natural language interface provides knowledge that can help interpret other multi-modal sensor data. We provide results highlighting the potential of our dialogue- and semantic similarity-based approach. We evaluate our work: (i) quantitatively, as an efficient way to seek users’ input for active learning of ADLs; and (ii) qualitatively, through a user study in which users were asked to compare our approach and an established method. Results show the potential of our approach as a hands-free interface for annotation of sensor data as part of an active learning system. We provide insights into the challenges of active learning for activity recognition under real-world conditions and identify potential ways to address them.","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2023-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82427498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Clarice Wang, Kathryn Wang, Andrew Bian, Rashidul Islam, Kamrun Keya, James R. Foulds, Shimei Pan
Currently, there is a surge of interest in fair Artificial Intelligence (AI) and Machine Learning (ML) research which aims to mitigate discriminatory bias in AI algorithms, e.g., along lines of gender, age, and race. While most research in this domain focuses on developing fair AI algorithms, in this work, we examine the challenges which arise when humans and fair AI interact. Our results show that due to an apparent conflict between human preferences and fairness, a fair AI algorithm on its own may be insufficient to achieve its intended results in the real world. Using college major recommendation as a case study, we build a fair AI recommender by employing gender debiasing machine learning techniques. Our offline evaluation showed that the debiased recommender makes fairer career recommendations without sacrificing its accuracy in prediction. Nevertheless, an online user study of more than 200 college students revealed that participants on average prefer the original biased system over the debiased system. Specifically, we found that perceived gender disparity is a determining factor for the acceptance of a recommendation. In other words, we cannot fully address the gender bias issue in AI recommendations without addressing the gender bias in humans. We conducted a follow-up survey to gain additional insights into the effectiveness of various design options that can help participants to overcome their own biases. Our results suggest that making fair AI explainable is crucial for increasing its adoption in the real world.
{"title":"When Biased Humans Meet Debiased AI: A Case Study in College Major Recommendation","authors":"Clarice Wang, Kathryn Wang, Andrew Bian, Rashidul Islam, Kamrun Keya, James R. Foulds, Shimei Pan","doi":"10.1145/3611313","DOIUrl":"https://doi.org/10.1145/3611313","url":null,"abstract":"Currently, there is a surge of interest in fair Artificial Intelligence (AI) and Machine Learning (ML) research which aims to mitigate discriminatory bias in AI algorithms, e.g., along lines of gender, age, and race. While most research in this domain focuses on developing fair AI algorithms, in this work, we examine the challenges which arise when humans and fair AI interact. Our results show that due to an apparent conflict between human preferences and fairness, a fair AI algorithm on its own may be insufficient to achieve its intended results in the real world. Using college major recommendation as a case study, we build a fair AI recommender by employing gender debiasing machine learning techniques. Our offline evaluation showed that the debiased recommender makes fairer career recommendations without sacrificing its accuracy in prediction. Nevertheless, an online user study of more than 200 college students revealed that participants on average prefer the original biased system over the debiased system. Specifically, we found that perceived gender disparity is a determining factor for the acceptance of a recommendation. In other words, we cannot fully address the gender bias issue in AI recommendations without addressing the gender bias in humans. We conducted a follow-up survey to gain additional insights into the effectiveness of various design options that can help participants to overcome their own biases. Our results suggest that making fair AI explainable is crucial for increasing its adoption in the real world.","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73796948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-24DOI: https://dl.acm.org/doi/10.1145/3610578
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 paper focuses on the effect of showing integrity. In particular, this paper 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.
{"title":"Integrity Based Explanations for Fostering Appropriate Trust in AI Agents","authors":"Siddharth Mehrotra, Carolina Centeio Jorge, Catholijn M. Jonker, Myrthe L. Tielman","doi":"https://dl.acm.org/doi/10.1145/3610578","DOIUrl":"https://doi.org/https://dl.acm.org/doi/10.1145/3610578","url":null,"abstract":"<p>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 paper focuses on the effect of showing integrity. In particular, this paper 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.</p>","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138508052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Siddharth Mehrotra, Carolina Centeio Jorge, C. Jonker, M. 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 paper focuses on the effect of showing integrity. In particular, this paper 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.
{"title":"Integrity Based Explanations for Fostering Appropriate Trust in AI Agents","authors":"Siddharth Mehrotra, Carolina Centeio Jorge, C. Jonker, M. Tielman","doi":"10.1145/3610578","DOIUrl":"https://doi.org/10.1145/3610578","url":null,"abstract":"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 paper focuses on the effect of showing integrity. In particular, this paper 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.","PeriodicalId":48574,"journal":{"name":"ACM Transactions on Interactive Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76625860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号