Author

Esther Boissin

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#small language model Open access Oct 2026

What beliefs are most debunkable?

Large language models (LLMs) can persuade people to revise their beliefs, but it is unclear which beliefs are most "debunkable," and why. Across three pooled studies, participants (N = 3,341 online U.S. adults) discussed a self-reported conspiracy or other epistemically suspect belief with GPT-4, instructed to debunk i...

Esther Boissin, Thomas H. Costello, David Gertler Rand et al. · 0 citations