Some selected publications are below. For a more complete list, see my Google Scholar profile
Current writing-support systems encourage writers to appropriate the language model’s output as their own words. Does it have to be that way? We explore of two new types of interactions with generative language models: enabling structural manipulation of already-drafted sentences, and offering questions rather than snippets to writers. We present early experiments on feasibility and suitability of these interactions.
In our lab study, image captions written with predictive text suggestions were shorter and included fewer words that that the system did not predict.
Intelligent systems make biased decisions because they are trained on biased data. Could these system biases affect what people create? We found that when writing restaurant reviews, biased system behavior leads to biased human behavior: People presented with phrasal text entry shortcuts that were skewed positive wrote more positive reviews than they did when presented with negative-skewed shortcuts.
We introduce a simple extension to the familiar mobile keyboard suggestion interface that presents phrase suggestions that can be accepted by a repeated-tap gesture. In an extended composition task, we found that phrases were interpreted as suggestions that affected the content of what participants wrote more than conventional single-word suggestions, which were interpreted as predictions.