Maria De-Arteaga
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Maria De-Arteaga has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
Artur Dubrawski
Auton Lab, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
3 shared publications- Jakob Schoeffer
University of Texas at Austin, Austin, TX, USA
3 shared publications - Artur Dubrawski
Carnegie Mellon University
2 shared publications - Charles E. Kahn
Department of Radiology, University of Pennsylvania, Philadelphia, PA
2 shared publications - Henning Müller
Informatics Institute, University of Applied Sciences Western Switzerland (HES-SO Valais), Sierre, Switzerland; Medical Faculty, University of Geneva, Geneva, Switzerland; The Sense Innovation and Research Center, Sion, Switzerland, Switzerland
2 shared publications Ivan Eggel
University of Applied Sciences Western Switzerland (HES-SO), Sierre, Switzerland
2 shared publications
Latest Publications
- Open Access
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 7769-7792
Fairness-Aware Multi-Group Target Detection in Online Discussion
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 7769-7792
Open AccessFairness-Aware Multi-Group Target Detection in Online Discussion
- 1 December 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 71 (12) , 10465-10485
Leveraging Expert Consistency to Improve Algorithmic Decision Support
Machine learning (ML) is increasingly being used to support high-stakes decisions. However, there is frequently a construct gap: a gap between the construct of interest to the decision-making task and what is captured in proxies used as labels to train ML models. As a result, ML models may fail to capture important dimensions of decision criteria, hampering their utility for decision support. Thus, an essential step in the design of ML systems for decision support is selecting a target label among available proxies. In this work, we explore the use of historical expert decisions as a rich—yet also imperfect—source of information that can be combined with observed outcomes to narrow the construct gap. We argue that managers and system designers may be interested in learning from experts in instances where they exhibit consistency with each other while learning from observed outcomes otherwise. We develop a methodology to enable this goal using information that is commonly available in organizational information systems. This involves two core steps. First, we propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data are assessed by a single expert. Second, we introduce a label amalgamation approach that allows ML models to simultaneously learn from expert decisions and observed outcomes. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap, yielding better predictive performance than learning from either observed outcomes or expert decisions alone. This paper was accepted by Anindya Ghose, information systems. Funding: This work was supported by the National Institutes of Health [Grant R01NS124642], Good Systems, University of Texas at Austin, the Metro 21 Institute, the Defense Advanced Research Projects Agency [Grant FA8750-17-2-0130], the National Science Foundation [Grant 1939606], Google [Award for Inclusion Research], and the UK Medical Research Council [Grants MC UU 00002/2, MC UU 00002/5, and MC UU 00040/02–Precision Medicine]. Supplemental Material: The online appendices and data files are available at https://doi.org/10.1287/mnsc.2022.01576 .
- 1 December 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
- Vol. 71 (12) , 10465-10485
Leveraging Expert Consistency to Improve Algorithmic Decision Support
Machine learning (ML) is increasingly being used to support high-stakes decisions. However, there is frequently a construct gap: a gap between the construct of interest to the decision-making task and what is captured in proxies used as labels to train ML models. As a result, ML models may fail to capture important dimensions of decision criteria, hampering their utility for decision support. Thus, an essential step in the design of ML systems for decision support is selecting a target label among available proxies. In this work, we explore the use of historical expert decisions as a rich—yet also imperfect—source of information that can be combined with observed outcomes to narrow the construct gap. We argue that managers and system designers may be interested in learning from experts in instances where they exhibit consistency with each other while learning from observed outcomes otherwise. We develop a methodology to enable this goal using information that is commonly available in organizational information systems. This involves two core steps. First, we propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data are assessed by a single expert. Second, we introduce a label amalgamation approach that allows ML models to simultaneously learn from expert decisions and observed outcomes. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap, yielding better predictive performance than learning from either observed outcomes or expert decisions alone. This paper was accepted by Anindya Ghose, information systems. Funding: This work was supported by the National Institutes of Health [Grant R01NS124642], Good Systems, University of Texas at Austin, the Metro 21 Institute, the Defense Advanced Research Projects Agency [Grant FA8750-17-2-0130], the National Science Foundation [Grant 1939606], Google [Award for Inclusion Research], and the UK Medical Research Council [Grants MC UU 00002/2, MC UU 00002/5, and MC UU 00040/02–Precision Medicine]. Supplemental Material: The online appendices and data files are available at https://doi.org/10.1287/mnsc.2022.01576 .
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1080-1094
Perils of Label Indeterminacy: A Case Study on Prediction of Neurological Recovery After Cardiac Arrest
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1080-1094
Open AccessPerils of Label Indeterminacy: A Case Study on Prediction of Neurological Recovery After Cardiac Arrest
- Top Cited PapersOpen Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1579-1595
A Critical Survey on Fairness Benefits of Explainable AI
In this critical survey, we analyze typical claims on the relationship between explainable AI (XAI) and fairness to disentangle the multidimensional relationship between these two concepts. Based on a systematic literature review and a subsequent qualitative content analysis, we identify seven archetypal claims from 175 scientific articles on the alleged fairness benefits of XAI. We present crucial caveats with respect to these claims and provide an entry point for future discussions around the potentials and limitations of XAI for specific fairness desiderata. Importantly, we notice that claims are often (i) vague and simplistic, (ii) lacking normative grounding, or (iii) poorly aligned with the actual capabilities of XAI. We suggest to conceive XAI not as an ethical panacea but as one of many tools to approach the multidimensional, sociotechnical challenge of algorithmic fairness. Moreover, when making a claim about XAI and fairness, we emphasize the need to be more specific about what kind of XAI method is used, which fairness desideratum it refers to, how exactly it enables fairness, and who is the stakeholder that benefits from XAI.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1579-1595
Top Cited PapersOpen AccessA Critical Survey on Fairness Benefits of Explainable AI
In this critical survey, we analyze typical claims on the relationship between explainable AI (XAI) and fairness to disentangle the multidimensional relationship between these two concepts. Based on a systematic literature review and a subsequent qualitative content analysis, we identify seven archetypal claims from 175 scientific articles on the alleged fairness benefits of XAI. We present crucial caveats with respect to these claims and provide an entry point for future discussions around the potentials and limitations of XAI for specific fairness desiderata. Importantly, we notice that claims are often (i) vague and simplistic, (ii) lacking normative grounding, or (iii) poorly aligned with the actual capabilities of XAI. We suggest to conceive XAI not as an ethical panacea but as one of many tools to approach the multidimensional, sociotechnical challenge of algorithmic fairness. Moreover, when making a claim about XAI and fairness, we emphasize the need to be more specific about what kind of XAI method is used, which fairness desideratum it refers to, how exactly it enables fairness, and who is the stakeholder that benefits from XAI.
- Top Cited PapersOpen Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
In this work, we study the effects of feature-based explanations on distributive fairness of AI-assisted decisions, specifically focusing on the task of predicting occupations from short textual bios. We also investigate how any effects are mediated by humans’ fairness perceptions and their reliance on AI recommendations. Our findings show that explanations influence fairness perceptions, which, in turn, relate to humans’ tendency to adhere to AI recommendations. However, we see that such explanations do not enable humans to discern correct and incorrect AI recommendations. Instead, we show that they may affect reliance irrespective of the correctness of AI recommendations. Depending on which features an explanation highlights, this can foster or hinder distributive fairness: when explanations highlight features that are task-irrelevant and evidently associated with the sensitive attribute, this prompts overrides that counter AI recommendations that align with gender stereotypes. Meanwhile, if explanations appear task-relevant, this induces reliance behavior that reinforces stereotype-aligned errors. These results imply that feature-based explanations are not a reliable mechanism to improve distributive fairness.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Top Cited PapersOpen AccessExplanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
In this work, we study the effects of feature-based explanations on distributive fairness of AI-assisted decisions, specifically focusing on the task of predicting occupations from short textual bios. We also investigate how any effects are mediated by humans’ fairness perceptions and their reliance on AI recommendations. Our findings show that explanations influence fairness perceptions, which, in turn, relate to humans’ tendency to adhere to AI recommendations. However, we see that such explanations do not enable humans to discern correct and incorrect AI recommendations. Instead, we show that they may affect reliance irrespective of the correctness of AI recommendations. Depending on which features an explanation highlights, this can foster or hinder distributive fairness: when explanations highlight features that are task-irrelevant and evidently associated with the sensitive attribute, this prompts overrides that counter AI recommendations that align with gender stereotypes. Meanwhile, if explanations appear task-relevant, this induces reliance behavior that reinforces stereotype-aligned errors. These results imply that feature-based explanations are not a reliable mechanism to improve distributive fairness.
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 3689-3700
Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection
Algorithmic bias often arises as a result of differential subgroup validity, in which predictive relationships vary across groups. For example, in toxic language detection, comments targeting different demographic groups can vary markedly across groups. In such settings, trained models can be dominated by the relationships that best fit the majority group, leading to disparate performance. We propose framing toxicity detection as multi-task learning (MTL), allowing a model to specialize on the relationships that are relevant to each demographic group while also leveraging shared properties across groups. With toxicity detection, each task corresponds to identifying toxicity against a particular demographic group. However, traditional MTL requires labels for all tasks to be present for every data point. To address this, we propose Conditional MTL (CondMTL), wherein only training examples relevant to the given demographic group are considered by the loss function. This lets us learn group specific representations in each branch which are not cross contaminated by irrelevant labels. Results on synthetic and real data show that using CondMTL improves predictive recall over various baselines in general and for the minority demographic group in particular, while having similar overall accuracy.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 3689-3700
Open AccessSame Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection
Algorithmic bias often arises as a result of differential subgroup validity, in which predictive relationships vary across groups. For example, in toxic language detection, comments targeting different demographic groups can vary markedly across groups. In such settings, trained models can be dominated by the relationships that best fit the majority group, leading to disparate performance. We propose framing toxicity detection as multi-task learning (MTL), allowing a model to specialize on the relationships that are relevant to each demographic group while also leveraging shared properties across groups. With toxicity detection, each task corresponds to identifying toxicity against a particular demographic group. However, traditional MTL requires labels for all tasks to be present for every data point. To address this, we propose Conditional MTL (CondMTL), wherein only training examples relevant to the given demographic group are considered by the loss function. This lets us learn group specific representations in each branch which are not cross contaminated by irrelevant labels. Results on synthetic and real data show that using CondMTL improves predictive recall over various baselines in general and for the minority demographic group in particular, while having similar overall accuracy.
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Human-Centered Responsible Artificial Intelligence: Current & Future Trends
In recent years, the CHI community has seen significant growth in research on Human-Centered Responsible Artificial Intelligence. While different research communities may use different terminology to discuss similar topics, all of this work is ultimately aimed at developing AI that benefits humanity while being grounded in human rights and ethics, and reducing the potential harms of AI. In this special interest group, we aim to bring together researchers from academia and industry interested in these topics to map current and future research trends to advance this important area of research by fostering collaboration and sharing ideas.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessHuman-Centered Responsible Artificial Intelligence: Current & Future Trends
In recent years, the CHI community has seen significant growth in research on Human-Centered Responsible Artificial Intelligence. While different research communities may use different terminology to discuss similar topics, all of this work is ultimately aimed at developing AI that benefits humanity while being grounded in human rights and ethics, and reducing the potential harms of AI. In this special interest group, we aim to bring together researchers from academia and industry interested in these topics to map current and future research trends to advance this important area of research by fostering collaboration and sharing ideas.
- Open Access
- 14 April 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (CSCW1) , 1-20
Toward Supporting Perceptual Complementarity in Human-AI Collaboration via Reflection on Unobservables
In many real world contexts, successful human-AI collaboration requires humans to productively integrate complementary sources of information into AI-informed decisions. However, in practice human decision-makers often lack understanding of what information an AI model has access to, in relation to themselves. There are few available guidelines regarding how to effectively communicate aboutunobservables: features that may influence the outcome, but which are unavailable to the model. In this work, we conducted an online experiment to understand whether and how explicitly communicating potentially relevant unobservables influences how people integrate model outputs and unobservables when making predictions. Our findings indicate that presenting prompts about unobservables can change how humans integrate model outputs and unobservables, but do not necessarily lead to improved performance. Furthermore, the impacts of these prompts can vary depending on decision-makers' prior domain expertise. We conclude by discussing implications for future research and design of AI-based decision support tools.
- 14 April 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (CSCW1) , 1-20
Open AccessToward Supporting Perceptual Complementarity in Human-AI Collaboration via Reflection on Unobservables
In many real world contexts, successful human-AI collaboration requires humans to productively integrate complementary sources of information into AI-informed decisions. However, in practice human decision-makers often lack understanding of what information an AI model has access to, in relation to themselves. There are few available guidelines regarding how to effectively communicate aboutunobservables: features that may influence the outcome, but which are unavailable to the model. In this work, we conducted an online experiment to understand whether and how explicitly communicating potentially relevant unobservables influences how people integrate model outputs and unobservables when making predictions. Our findings indicate that presenting prompts about unobservables can change how humans integrate model outputs and unobservables, but do not necessarily lead to improved performance. Furthermore, the impacts of these prompts can vary depending on decision-makers' prior domain expertise. We conclude by discussing implications for future research and design of AI-based decision support tools.
- Open Access
Social Norm Bias: Residual Harms of Fairness-Aware Algorithms
Many modern machine learning algorithms mitigate bias by enforcing fairness constraints across coarsely-defined groups related to a sensitive attribute like gender or race. However, these algorithms seldom account for within-group heterogeneity and biases that may disproportionately affect some members of a group. In this work, we characterize Social Norm Bias (SNoB), a subtle but consequential type of algorithmic discrimination that may be exhibited by machine learning models, even when these systems achieve group fairness objectives. We study this issue through the lens of gender bias in occupation classification. We quantify SNoB by measuring how an algorithm's predictions are associated with conformity to inferred gender norms. When predicting if an individual belongs to a male-dominated occupation, this framework reveals that "fair" classifiers still favor biographies written in ways that align with inferred masculine norms. We compare SNoB across algorithmic fairness methods and show that it is frequently a residual bias, and post-processing approaches do not mitigate this type of bias at all.
Open AccessSocial Norm Bias: Residual Harms of Fairness-Aware Algorithms
Many modern machine learning algorithms mitigate bias by enforcing fairness constraints across coarsely-defined groups related to a sensitive attribute like gender or race. However, these algorithms seldom account for within-group heterogeneity and biases that may disproportionately affect some members of a group. In this work, we characterize Social Norm Bias (SNoB), a subtle but consequential type of algorithmic discrimination that may be exhibited by machine learning models, even when these systems achieve group fairness objectives. We study this issue through the lens of gender bias in occupation classification. We quantify SNoB by measuring how an algorithm's predictions are associated with conformity to inferred gender norms. When predicting if an individual belongs to a male-dominated occupation, this framework reveals that "fair" classifiers still favor biographies written in ways that align with inferred masculine norms. We compare SNoB across algorithmic fairness methods and show that it is frequently a residual bias, and post-processing approaches do not mitigate this type of bias at all.
- Top Cited PapersOpen Access
- 1 January 2022
- Published by SAGE Publications in Big Data & Society
- Vol. 9 (1)
Diversity in sociotechnical machine learning systems
There has been a surge of recent interest in sociocultural diversity in machine learning research. Currently, however, there is a gap between discussions of measures and benefits of diversity in machine learning, on the one hand, and the broader research on the underlying concepts of diversity and the precise mechanisms of its functional benefits, on the other. This gap is problematic because diversity is not a monolithic concept. Rather, different concepts of diversity are based on distinct rationales that should inform how we measure diversity in a given context. Similarly, the lack of specificity about the precise mechanisms underpinning diversity’s potential benefits can result in uninformative generalities, invalid experimental designs, and illicit interpretations of findings. In this work, we draw on research in philosophy, psychology, and social and organizational sciences to make three contributions: First, we introduce a taxonomy of different diversity concepts from philosophy of science, and explicate the distinct epistemic and political rationales underlying these concepts. Second, we provide an overview of mechanisms by which diversity can benefit group performance. Third, we situate these taxonomies of concepts and mechanisms in the lifecycle of sociotechnical machine learning systems and make a case for their usefulness in fair and accountable machine learning. We do so by illustrating how they clarify the discourse around diversity in the context of machine learning systems, promote the formulation of more precise research questions about diversity’s impact, and provide conceptual tools to further advance research and practice.
- 1 January 2022
- Published by SAGE Publications in Big Data & Society
- Vol. 9 (1)
Top Cited PapersOpen AccessDiversity in sociotechnical machine learning systems
There has been a surge of recent interest in sociocultural diversity in machine learning research. Currently, however, there is a gap between discussions of measures and benefits of diversity in machine learning, on the one hand, and the broader research on the underlying concepts of diversity and the precise mechanisms of its functional benefits, on the other. This gap is problematic because diversity is not a monolithic concept. Rather, different concepts of diversity are based on distinct rationales that should inform how we measure diversity in a given context. Similarly, the lack of specificity about the precise mechanisms underpinning diversity’s potential benefits can result in uninformative generalities, invalid experimental designs, and illicit interpretations of findings. In this work, we draw on research in philosophy, psychology, and social and organizational sciences to make three contributions: First, we introduce a taxonomy of different diversity concepts from philosophy of science, and explicate the distinct epistemic and political rationales underlying these concepts. Second, we provide an overview of mechanisms by which diversity can benefit group performance. Third, we situate these taxonomies of concepts and mechanisms in the lifecycle of sociotechnical machine learning systems and make a case for their usefulness in fair and accountable machine learning. We do so by illustrating how they clarify the discourse around diversity in the context of machine learning systems, promote the formulation of more precise research questions about diversity’s impact, and provide conceptual tools to further advance research and practice.