Madeleine Grunde-McLaughlin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Madeleine Grunde-McLaughlin has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Jeffrey Heer
Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, Washington, USA
3 shared publications - Ranjay Krishna
University of Washington, USA
3 shared publications - Daniel Sabby Weld
Allen Institute for AI, Seattle, USA
2 shared publications - Nino Migineishvili
University of Washington, Seattle, Washington, USA
2 shared publications - Andrew McNutt
Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, Utah, USA
1 shared publication - Emily Reif
Google research
1 shared publication
Latest Publications
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 683-698
RDoFlow: Automatically assessing under-specified statistical analyses in HCI
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 683-698
Open AccessRDoFlow: Automatically assessing under-specified statistical analyses in HCI
- Open Access
- 25 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 33 (1) , 1-35
Wildfire and Forest Management: Opportunities for HCI Research
Wildfire and forest management increasingly rely on geospatial technologies, i.e., data and tools contributing to the geographic mapping and analysis of the Earth, to inform measures for the control of wildfires. Nevertheless, challenges arising from domain experts adopting these complex, non-intuitive technologies are not well understood. We interviewed 12 participants in wildfire and forest management to explore the technical and socio-technical nature of these challenges, revealing that (1) knowledge and data are fragmented across stakeholders, ranging from governmental agencies to small landowners. This fragmentation causes participants to (2) struggle in sharing knowledge and expertise. Participants (3) voice concerns about model bias since decisions informed by geospatial technologies can have far-reaching impacts. Yet, they (4) face barriers engaging people most impacted by these decisions. We detail an HCI research agenda that includes: exploring opportunities to connect stakeholders and sharing knowledge, standardizing decision-making, and engaging local communities.
- 25 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 33 (1) , 1-35
Open AccessWildfire and Forest Management: Opportunities for HCI Research
Wildfire and forest management increasingly rely on geospatial technologies, i.e., data and tools contributing to the geographic mapping and analysis of the Earth, to inform measures for the control of wildfires. Nevertheless, challenges arising from domain experts adopting these complex, non-intuitive technologies are not well understood. We interviewed 12 participants in wildfire and forest management to explore the technical and socio-technical nature of these challenges, revealing that (1) knowledge and data are fragmented across stakeholders, ranging from governmental agencies to small landowners. This fragmentation causes participants to (2) struggle in sharing knowledge and expertise. Participants (3) voice concerns about model bias since decisions informed by geospatial technologies can have far-reaching impacts. Yet, they (4) face barriers engaging people most impacted by these decisions. We detail an HCI research agenda that includes: exploring opportunities to connect stakeholders and sharing knowledge, standardizing decision-making, and engaging local communities.
- Open Access
- 14 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 32 (3) , 1-57
Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows
LLM chains enable complex tasks by decomposing work into a sequence of subtasks. Similarly, the more established techniques of crowdsourcing workflows decompose complex tasks into smaller tasks for human crowdworkers. Chains address LLM errors analogously to the way crowdsourcing workflows address human error. To characterize opportunities for LLM chaining, we survey 107 papers across the crowdsourcing and chaining literature to construct a design space for chain development. The design space covers a designer’s objectives and the tactics used to build workflows. We then surface strategies that mediate how workflows use tactics to achieve objectives. To explore how techniques from crowdsourcing may apply to chaining, we adapt crowdsourcing workflows to implement LLM chains across three case studies: creating a taxonomy, shortening text, and writing a short story. From the design space and our case studies, we identify takeaways for effective chain design and raise implications for future research and development.
- 14 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computer-Human Interaction
- Vol. 32 (3) , 1-57
Open AccessDesigning LLM Chains by Adapting Techniques from Crowdsourcing Workflows
LLM chains enable complex tasks by decomposing work into a sequence of subtasks. Similarly, the more established techniques of crowdsourcing workflows decompose complex tasks into smaller tasks for human crowdworkers. Chains address LLM errors analogously to the way crowdsourcing workflows address human error. To characterize opportunities for LLM chaining, we survey 107 papers across the crowdsourcing and chaining literature to construct a design space for chain development. The design space covers a designer’s objectives and the tactics used to build workflows. We then surface strategies that mediate how workflows use tactics to achieve objectives. To explore how techniques from crowdsourcing may apply to chaining, we adapt crowdsourcing workflows to implement LLM chains across three case studies: creating a taxonomy, shortening text, and writing a short story. From the design space and our case studies, we identify takeaways for effective chain design and raise implications for future research and development.
- Top Cited PapersOpen Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-22
How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Study
Data analysis is challenging as analysts must navigate nuanced decisions that may yield divergent conclusions. AI assistants have the potential to support analysts in planning their analyses, enabling more robust decision making. Though AI-based assistants that target code execution (e.g., Github Copilot) have received significant attention, limited research addresses assistance for both analysis execution and planning. In this work, we characterize helpful planning suggestions and their impacts on analysts’ workflows. We first review the analysis planning literature and crowd-sourced analysis studies to categorize suggestion content. We then conduct a Wizard-of-Oz study (n=13) to observe analysts’ preferences and reactions to planning assistance in a realistic scenario. Our findings highlight subtleties in contextual factors that impact suggestion helpfulness, emphasizing design implications for supporting different abstractions of assistance, forms of initiative, increased engagement, and alignment of goals between analysts and assistants.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Top Cited PapersOpen AccessHow Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Study
Data analysis is challenging as analysts must navigate nuanced decisions that may yield divergent conclusions. AI assistants have the potential to support analysts in planning their analyses, enabling more robust decision making. Though AI-based assistants that target code execution (e.g., Github Copilot) have received significant attention, limited research addresses assistance for both analysis execution and planning. In this work, we characterize helpful planning suggestions and their impacts on analysts’ workflows. We first review the analysis planning literature and crowd-sourced analysis studies to categorize suggestion content. We then conduct a Wizard-of-Oz study (n=13) to observe analysts’ preferences and reactions to planning assistance in a realistic scenario. Our findings highlight subtleties in contextual factors that impact suggestion helpfulness, emphasizing design implications for supporting different abstractions of assistance, forms of initiative, increased engagement, and alignment of goals between analysts and assistants.
- Top Cited PapersOpen Access
- 14 April 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (CSCW1) , 1-38
Explanations Can Reduce Overreliance on AI Systems During Decision-Making
Prior work has identified a resilient phenomenon that threatens the performance of human-AI decision-making teams: overreliance, when people agree with an AI, even when it is incorrect. Surprisingly, overreliance does not reduce when the AI produces explanations for its predictions, compared to only providing predictions. Some have argued that overreliance results from cognitive biases or uncalibrated trust, attributing overreliance to an inevitability of human cognition. By contrast, our paper argues that people strategically choose whether or not to engage with an AI explanation, demonstrating empirically that there are scenarios where AI explanations reduce overreliance. To achieve this, we formalize this strategic choice in a cost-benefit framework, where the costs and benefits of engaging with the task are weighed against the costs and benefits of relying on the AI. We manipulate the costs and benefits in a maze task, where participants collaborate with a simulated AI to find the exit of a maze. Through 5 studies (N = 731), we find that costs such as task difficulty (Study 1), explanation difficulty (Study 2, 3), and benefits such as monetary compensation (Study 4) affect overreliance. Finally, Study 5 adapts the Cognitive Effort Discounting paradigm to quantify the utility of different explanations, providing further support for our framework. Our results suggest that some of the null effects found in literature could be due in part to the explanation not sufficiently reducing the costs of verifying the AI's prediction.
- 14 April 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (CSCW1) , 1-38
Top Cited PapersOpen AccessExplanations Can Reduce Overreliance on AI Systems During Decision-Making
Prior work has identified a resilient phenomenon that threatens the performance of human-AI decision-making teams: overreliance, when people agree with an AI, even when it is incorrect. Surprisingly, overreliance does not reduce when the AI produces explanations for its predictions, compared to only providing predictions. Some have argued that overreliance results from cognitive biases or uncalibrated trust, attributing overreliance to an inevitability of human cognition. By contrast, our paper argues that people strategically choose whether or not to engage with an AI explanation, demonstrating empirically that there are scenarios where AI explanations reduce overreliance. To achieve this, we formalize this strategic choice in a cost-benefit framework, where the costs and benefits of engaging with the task are weighed against the costs and benefits of relying on the AI. We manipulate the costs and benefits in a maze task, where participants collaborate with a simulated AI to find the exit of a maze. Through 5 studies (N = 731), we find that costs such as task difficulty (Study 1), explanation difficulty (Study 2, 3), and benefits such as monetary compensation (Study 4) affect overreliance. Finally, Study 5 adapts the Cognitive Effort Discounting paradigm to quantify the utility of different explanations, providing further support for our framework. Our results suggest that some of the null effects found in literature could be due in part to the explanation not sufficiently reducing the costs of verifying the AI's prediction.