Explainable AI is important to build trustworthy and understandable systems. To aid understanding, explanations need to be relatable, but current techniques remain overly technical with obscure information. Drawing from the …
Just as AI performance degrades with data corruptions, we found that so does explanation faithfulness. For example, blurring an image can provide privacy, but this leads to heatmap explanations becoming …
Previously, we improved creativity by automatically directing the crowd with diverse prompts Directed Diversity (Cox et al., CHI’21). Here, we further improve creativity by providing real-time feedback on the ideations. …
The successful deployment of artificial intelligence (AI) in many domains from healthcare to hiring requires their responsible use, particularly in model explanations and privacy. Explainable artificial intelligence (XAI) provides more …
Feature attribution is widely used to explain how influential each measured input feature value is for an output inference. However, measurements can be uncertain, and it is unclear how the …
Crowd sourcing can obtain many creative ideas, but without careful coordination, many ideators may generate the same ideas. This leads to redundancy and limits the diversity of ideas from the …
Consider searching for cheap hotel at a good location on a travel website. You can sort hotels by price, but the locations can either be near or far from your …
Our paper on the city-scale data analysis of population step count behavior has won the Distinguished Paper Award in PACM IMWUT Vol. 3. Among 6 awarded from 166 total papers …
Explanations of artificial explanations can be simplified by controlling the number of variables, but the complexity in how they are visualized can still impede quick interpretation. We quantitatively modeled the …
OD Bundling is a popular technique to visualize key patterns in movement flows, but the curves illustrated can be misleading by suggesting paths that do not match true or plausible …