MGMadeleine Grunde-McLaughlin

Madeleine Grunde-McLaughlin

*This is an algorithmically generated author record based on publicly available information.

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:


Latest Publications

  • Open Access

    RDoFlow: Automatically assessing under-specified statistical analyses in HCI

    by Madeleine Grunde-McLaughlin, Weixuan Liu, Ria Patil, Nino Migineishvili, Emily Reif, Ranjay Krishna, Daniel S. Weld, Jeffrey Heer

  • Open Access

    Wildfire and Forest Management: Opportunities for HCI Research

    by Nino Migineishvili, Madeleine Grunde-McLaughlin, Emmanuel Azuh, Spencer Wood, René Just, Katharina Reinecke

    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

    Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows

    by Madeleine Grunde-McLaughlin, Michelle S. Lam, Ranjay Krishna, Daniel S. Weld, Jeffrey Heer

    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 Papers
    Open Access

    How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Study

    by Ken Gu, Madeleine Grunde-McLaughlin, Andrew McNutt, Jeffrey Heer, Tim Althoff

    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 Papers
    Open Access

    Explanations Can Reduce Overreliance on AI Systems During Decision-Making

    by Helena Vasconcelos, Matthew Jörke, Madeleine Grunde-McLaughlin, Tobias Gerstenberg, Michael S. Bernstein, Ranjay Krishna

    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.