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-articleOctober 2024
FathomGPT: A natural language interface for interactively exploring ocean science data
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 95, Pages 1–15https://doi.org/10.1145/3654777.3676462We introduce FathomGPT, an open source system for the interactive investigation of ocean science data via a natural language interface. FathomGPT was developed in close collaboration with marine scientists to enable researchers to explore and analyze ...
- research-articleOctober 2024
Natural Expression of a Machine Learning Model's Uncertainty Through Verbal and Non-Verbal Behavior of Intelligent Virtual Agents
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 130, Pages 1–15https://doi.org/10.1145/3654777.3676454Uncertainty cues are inherent in natural human interaction, as they signal to communication partners how much they can rely on conveyed information. Humans subconsciously provide such signals both verbally (e.g., through expressions such as “maybe’’ or “...
- research-articleOctober 2024
Beyond the Chat: Executable and Verifiable Text-Editing with LLMs
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 20, Pages 1–23https://doi.org/10.1145/3654777.3676419Conversational interfaces powered by Large Language Models (LLMs) have recently become a popular way to obtain feedback during document editing. However, standard chat-based conversational interfaces cannot explicitly surface the editing changes that ...
- research-articleOctober 2024
WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 119, Pages 1–14https://doi.org/10.1145/3654777.3676374Large language models (LLMs) support data analysis through conversational user interfaces, as exemplified in OpenAI’s ChatGPT (formally known as Advanced Data Analysis or Code Interpreter). Essentially, LLMs produce code for accomplishing diverse ...
- research-articleOctober 2024
Clarify: Improving Model Robustness With Natural Language Corrections
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 133, Pages 1–19https://doi.org/10.1145/3654777.3676362The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data. To prevent such misconceptions, we must necessarily provide additional ...
- research-articleOctober 2024
CoLadder: Manipulating Code Generation via Multi-Level Blocks
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 11, Pages 1–20https://doi.org/10.1145/3654777.3676357This paper adopted an iterative design process to gain insights into programmers’ strategies when using LLMs for programming. We proposed CoLadder, a novel system that supports programmers by facilitating hierarchical task decomposition, direct code ...
- research-articleOctober 2024
GPTVoiceTasker: Advancing Multi-step Mobile Task Efficiency Through Dynamic Interface Exploration and Learning
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 48, Pages 1–17https://doi.org/10.1145/3654777.3676356Virtual assistants have the potential to play an important role in helping users achieves different tasks. However, these systems face challenges in their real-world usability, characterized by inefficiency and struggles in grasping user intentions. ...
- research-articleOctober 2024
Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition
- Majeed Kazemitabaar,
- Jack Williams,
- Ian Drosos,
- Tovi Grossman,
- Austin Zachary Henley,
- Carina Negreanu,
- Advait Sarkar
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 92, Pages 1–19https://doi.org/10.1145/3654777.3676345LLM-powered tools like ChatGPT Data Analysis, have the potential to help users tackle the challenging task of data analysis programming, which requires expertise in data processing, programming, and statistics. However, our formative study (n=15) ...
- research-articleOctober 2024
DrawTalking: Building Interactive Worlds by Sketching and Speaking
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and TechnologyArticle No.: 76, Pages 1–25https://doi.org/10.1145/3654777.3676334We introduce DrawTalking, an approach to building and controlling interactive worlds by sketching and speaking while telling stories. It emphasizes user control and flexibility, and gives programming-like capability without requiring code. An early open-...