More Like this

1. Polite AI mitigates user susceptibility to AI hallucinations

   https://doi.org/10.1080/00140139.2024.2434604  

   Pak, Richard; Rovira, Ericka; McLaughlin, Anne (November 2024, Ergonomics)

   With their increased capability, AI-based chatbots have become increasingly popular tools to help users answer complex queries. However, these chatbots may hallucinate, or generate incorrect but very plausible-sounding information, more frequently than previously thought. Thus, it is crucial to examine strategies to mitigate human susceptibility to hallucinated output. In a between-subjects experiment, participants completed a difficult quiz with assistance from either a polite or neutral-toned AI chatbot, which occasionally provided hallucinated (incorrect) information. Signal detection analysis revealed that participants interacting with polite-AI showed modestly higher sensitivity in detecting hallucinations and a more conservative response bias compared to those interacting with neutral-toned AI. While the observed effect sizes were modest, even small improvements in users’ ability to detect AI hallucinations can have significant consequences, particularly in high-stakes domains or when aggregated across millions of AI interactions. 

   more » « less
2. The AI-DEC: A Card-based Design Method for User-centered AI Explanations

   https://doi.org/10.1145/3643834.3661576  

   Lee, Christine P; Lee, Min Kyung; Mutlu, Bilge (July 2024, ACM)
3. A User Interface to Communicate Interpretable AI Decisions to Radiologists

   https://doi.org/10.1117/12.2654068  

   Ou, Yanchen Jessie; Barnett, Alina J.; Mitra, Anika; Schwartz, Fides R.; Chen, Chaofan; Grimm, Lars; Lo, Joseph Y.; Rudin, Cynthia (April 2023, Medical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment)

   Chen, Yan; Mello-Thoms, Claudia R. (Ed.)

   Tools for computer-aided diagnosis based on deep learning have become increasingly important in the medical field. Such tools can be useful, but require effective communication of their decision-making process in order to safely and meaningfully guide clinical decisions. We present a user interface that incorporates the IAIA-BL model, which interpretably predicts both mass margin and malignancy for breast lesions. The user interface displays the most relevant aspects of the model’s explanation including the predicted margin value, the AI confidence in the prediction, and the two most highly activated prototypes for each case. In addition, this user interface includes full-field and cropped images of the region of interest, as well as a questionnaire suitable for a reader study. Our preliminary results indicate that the model increases the readers’ confidence and accuracy in their decisions on margin and malignancy. 

   more » « less
4. Undermining User Privacy on Mobile Devices Using AI

   https://doi.org/10.1145/3321705.3329804  

   Gulmezoglu, Berk; Zankl, Andreas; Tol, M. Caner; Islam, Saad; Eisenbarth, Thomas; Sunar, Berk (January 2019, Proceedings of the 2019 ACM Asia Conference on Computer and Communications Security)
5. How Mock Model Training Enhances User Perceptions of AI Systems

   Mahmood, Amama; Ajaykumar, Gopika; Huang, Chien-Ming (November 2021, Human Centered AI (HCAI) workshop at NeurIPS (2021))

   Artificial Intelligence (AI) is an integral part of our daily technology use and will likely be a critical component of emerging technologies. However, negative user preconceptions may hinder adoption of AI-based decision making. Prior work has highlighted the potential of factors such as transparency and explainability in improving user perceptions of AI. We further contribute to work on improving user perceptions of AI by demonstrating that bringing the user in the loop through mock model training can improve their perceptions of an AI agent’s capability and their comfort with the possibility of using technology employing the AI agent. 

   more » « less