Reproduce “Should We Tailor the Talk? Understanding the Impact of Conversational Styles on Preference Elicitation in Conversational Recommender Systems” 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

Ivica Kostric, Krisztian Balog, Ujwal Gadiraju

The authors compare conversational styles in a scientific-paper recommender while keeping its recommendation algorithm constant. In a study of 30 computer-science graduate students, bookmark relevance varied by topic domain: among participants assigned physics topics, the low-familiarity group’s mean bookmark-relevance score was 1.25 for Agency and 0.66 for HighInv. The style-by-domain interaction was significant, but no style was universally superior.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.