Reproduce “Improving understanding and trust in AI: How users benefit from interval-based counterfactual explanations” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tabea E. Röber, Paul Festor, Rob Goedhart, S. İlker Birbil, Aldo Faisal
The authors test whether interval counterfactual explanations affect house-price estimation and AI reliance. In an online study, 236 participants completed housing tasks with different explanations. The interval group had lower estimation error than the no-explanation group and chose AI more often when all features were visible. These results do not establish superiority over point explanations or warranted trust.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.