Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleApril 2024
AI Comes Out of the Closet: Using AI-Generated Virtual Characters to Help Individuals Practice LGBTQIA+ Advocacy
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 686–698https://doi.org/10.1145/3640543.3645213Despite significant historical progress, discrimination and social stigma continue to impact the lives of LGBTQIA+ individuals. The use of AI-generated virtual characters offers a unique opportunity to facilitate advocacy by engaging individuals in ...
- research-articleApril 2024
The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 155–180https://doi.org/10.1145/3640543.3645210AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against some protected ...
- research-articleApril 2024
Accuracy-Time Tradeoffs in AI-Assisted Decision Making under Time Pressure
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 138–154https://doi.org/10.1145/3640543.3645206In settings where users both need high accuracy and are time-pressured, such as doctors working in emergency rooms, we want to provide AI assistance that both increases decision accuracy and reduces decision-making time. Current literature focusses on ...
- research-articleApril 2024
Benefits of Human-AI Interaction for Expert Users Interacting with Prediction Models: a Study on Marathon Running
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 245–258https://doi.org/10.1145/3640543.3645205Users with large domain knowledge can be reluctant to use prediction models. This also applies to the sports domain, where running coaches rarely rely on marathon prediction tools for race-plan advice for their runners’ next marathon. This paper studies ...
- research-articleApril 2024
Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 288–303https://doi.org/10.1145/3640543.3645200Large Language Model (LLM) assistants, such as ChatGPT, have emerged as potential alternatives to search methods for helping users navigate complex, feature-rich software. LLMs use vast training data from domain-specific texts, software manuals, and code ...
- research-articleApril 2024
Enhancing AI-Assisted Group Decision Making through LLM-Powered Devil's Advocate
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 103–119https://doi.org/10.1145/3640543.3645199Group decision making plays a crucial role in our complex and interconnected world. The rise of AI technologies has the potential to provide data-driven insights to facilitate group decision making, although it is found that groups do not always utilize ...
- research-articleApril 2024
Take It, Leave It, or Fix It: Measuring Productivity and Trust in Human-AI Collaboration
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 370–384https://doi.org/10.1145/3640543.3645198Although recent developments in generative AI have greatly enhanced the capabilities of conversational agents such as Google’s Bard or OpenAI’s ChatGPT, it’s unclear whether the usage of these agents aids users across various contexts. To better ...
- research-articleApril 2024
SoK: An Exhaustive Taxonomy of Display Issues for Mobile Applications
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 537–548https://doi.org/10.1145/3640543.3645193Display issues, often arising from design inconsistencies or software problems, can have a significant impact on both user experience and system functionality. This study focuses on three primary challenges in the field of display issues: the absence of ...
- research-articleApril 2024
From Text to Pixels: Enhancing User Understanding through Text-to-Image Model Explanations
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 74–87https://doi.org/10.1145/3640543.3645173Recent progress in Text-to-Image (T2I) models promises transformative applications in art, design, education, medicine, and entertainment. These models, exemplified by Dall-e, Imagen, and Stable Diffusion, have the potential to revolutionize various ...
- research-articleApril 2024
Comparing Teaching Strategies of a Machine Learning-based Prosthetic Arm
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 715–730https://doi.org/10.1145/3640543.3645170Pattern-recognition-based arm prostheses rely on recognizing muscle activation to trigger movements. The effectiveness of this approach depends not only on the performance of the machine learner but also on the user’s understanding of its recognition ...
- research-articleApril 2024
The Trust Recovery Journey. The Effect of Timing of Errors on the Willingness to Follow AI Advice.
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 609–622https://doi.org/10.1145/3640543.3645167Complementing human decision-making with AI advice offers substantial advantages. However, humans do not always trust AI advice appropriately and are overly sensitive to incidental AI errors, even in cases with overall good performance. Today’s research ...
- research-articleApril 2024
Snapper: Accelerating Bounding Box Annotation in Object Detection Tasks with Find-and-Snap Tooling
- Alex C Williams,
- Min Bai,
- Jonathan Buck,
- Tristan J Mckinney,
- Amy Rechkemmer,
- Koushik Kalyanaraman,
- Matthew Lease,
- Patrick Haffner,
- Xiong Zhou,
- Erran Li
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 471–488https://doi.org/10.1145/3640543.3645162Object detection tasks are central to the development of datasets and algorithms in computer vision and machine learning. Despite its centrality, object detection remains tedious and time-consuming due to the inherent interactions that are often ...
- research-articleApril 2024
ReviewFlow: Intelligent Scaffolding to Support Academic Peer Reviewing
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 120–137https://doi.org/10.1145/3640543.3645159Peer review is a cornerstone of science. Research communities conduct peer reviews to assess contributions and to improve the overall quality of science work. Every year, new community members are recruited as peer reviewers for the first time. How could ...
- research-articleApril 2024
Understanding Novice's Annotation Process For 3D Semantic Segmentation Task With Human-In-The-Loop
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 444–454https://doi.org/10.1145/3640543.3645150Large-scale 3D point clouds are often used as training data for 3D semantic segmentation, but the labor-intensive nature of the annotation process challenges the acquisition of sufficient labeled data. Meanwhile, there has been limited research on ...
- research-articleApril 2024
Understanding Users’ Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Level
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 385–404https://doi.org/10.1145/3640543.3645148Large language models (LLMs) with chat-based capabilities, such as ChatGPT, are widely used in various workflows. However, due to a limited understanding of these large-scale models, users struggle to use this technology and experience different kinds ...
- research-articleApril 2024
ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles
- Savvas Petridis,
- Benjamin D Wedin,
- James Wexler,
- Mahima Pushkarna,
- Aaron Donsbach,
- Nitesh Goyal,
- Carrie J Cai,
- Michael Terry
IUI '24: Proceedings of the 29th International Conference on Intelligent User InterfacesMarch 2024, Pages 853–868https://doi.org/10.1145/3640543.3645144Large language model (LLM) prompting is a promising new approach for users to create and customize their own chatbots. However, current methods for steering a chatbot’s outputs, such as prompt engineering and fine-tuning, do not support users in ...