Reproduce “Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation” 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
Lex Konnelly, Elena Khasanova, Riqiang Wang, Matthias Lee, Harsh Saini, Parsa Kavehzadeh
The authors test whether specifying simulated customer personas through measurable language habits improves evaluation in customer-service interactions. Their schema assigns rate levels to eight features, and they compare it with descriptive archetype prompts using distinguishability and adherence measures. For gpt-5-mini, both measures rise, but gains occur in six of ten models; the metrics do not establish naturalness or real-user fidelity.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.