Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior
Main Authors: | Boggust, Angie, Hoover, Benjamin, Satyanarayan, Arvind, Strobelt, Hendrik |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
Format: | Article |
Language: | English |
Published: |
ACM|CHI Conference on Human Factors in Computing Systems
2022
|
Online Access: | https://hdl.handle.net/1721.1/146250 |
Similar Items
-
Saliency Cards: A Framework to Characterize and Compare Saliency Methods
by: Boggust, Angie, et al.
Published: (2023) -
Embedding Comparator: Visualizing Differences in Global Structure and Local Neighborhoods via Small Multiples
by: Boggust, Angie, et al.
Published: (2022) -
External validation of AI models in health should be replaced with recurring local validation
by: Youssef, A, et al.
Published: (2023) -
Classifying human promoters by occupancy patterns identifies recurring sequence elements, combinatorial binding, and spatial interactions
by: Xinyi Yang, et al.
Published: (2018-11-01) -
Recurring Themes
by: Michael J. Imperiale
Published: (2020-08-01)