Mapping the challenges of HCI: An application and evaluation of ChatGPT and GPT-4 for cost-efficient question answering

J Oppenlaender, J Hämäläinen - arXiv preprint arXiv:2306.05036, 2023 - arxiv.org
Large language models (LLMs), such as ChatGPT and GPT-4, are gaining wide-spread real
world use. Yet, the two LLMs are closed source, and little is known about the LLMs' …

A survey of visual analytics research for improving training data quality

W Yang, C Chen, J Zhu, L Li, P Liu, S Liu - Journal of Computer-Aided …, 2023 - jcad.cn
In the applications of machine learning, it is difficult to ensure the quality of training data due
to the various sources of training data and the inexperience of some annotators. By tightly …

ScatterUQ: interactive uncertainty visualizations for multiclass deep learning problems

HX Li, S Jorgensen, J Holodnak… - … IEEE Visualization and …, 2023 - ieeexplore.ieee.org
Recently, uncertainty-aware deep learning methods for multiclass labeling problems have
been developed that provide calibrated class prediction probabilities and out-of-distribution …

基于可视分析的训练数据质量提升综述

杨维铠, 陈长建, 朱江宁, 李磊, 刘鹏, 刘世霞 - 计算机辅助设计与图形学 …, 2023 - jcad.cn
在机器学习应用中, 由于数据来源渠道多以及部分标注者水平不足, 训练数据质量很难得到保证.
通过深度结合机器学习和可视化技术, 可视分析技术将人融入数据质量分析与提升回路中 …

Not What I was Trained for Out-of-Distribution-Tests for Interactive Als

B Severin, O Werger, M Hesenius - … Computer Systems. EICS …, 2024 - books.google.com
Recent advances in AI demonstrate its capacities to not only automate more and more
everyday tasks, but also make direct Human-AI-Interaction possible. When using AI models …

Not What I was Trained for–Out-of-Distribution-Tests for Interactive AIs

B Severin, O Werger, M Hesenius - International Symposium on …, 2023 - Springer
Recent advances in AI demonstrate its capacities to not only automate more and more
everyday tasks, but also make direct Human-AI-Interaction possible. When using AI models …