Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation

2026-10-07

AI Summary

This study addresses the low fidelity of user simulators and their reliance on costly, subjective LLM-based evaluation by proposing an objective assessment framework grounded in sociolinguistics. Methodologically, personality is reconceptualized as observable linguistic style rather than a label prediction task, enabling deterministic measurement through specific style rates. By integrating stylometric and lexicon-based analysis techniques, the framework introduces model-free validation tools for objective diagnostics. Experimental results demonstrate that this approach significantly enhances both style adherence and discriminability across most models, offering a novel pathway for precisely identifying simulation errors and generating diverse user profiles.

Abstract

As agentic systems gain commercial popularity, user simulators increasingly serve as measurement instrument for their evaluation. However, the fidelity of simulated users in comparison to real human users is generally low, and typically assessed by costly, subjective LLM judges. In this pilot study, we ask whether fidelity can instead be measured deterministically by treating a user persona sociolinguistically: as a social type that emerges from observable linguistic style, rather than one predicted by labels or descriptions a model must extrapolate into behaviour. We author personas as concrete stylistic rates, which lets us transfer two established, model-free instruments -- authorship-verification stylometry and lexicon-based content analysis -- as fidelity diagnostics. We A/B-test the sociolinguistic schema against a flat descriptive baseline across five task-oriented customer-service agents. Results show that the sociolinguistic schema improves both stylistic adherence and stylometric distinguishability for most of the tested models, with a caveat that persona style fidelity does not necessarily equal persona "naturalness". We argue that a sociolinguistic approach to persona design is a promising path towards more diverse and representative user personas, and that these metrics are most valuable in an error-attribution analysis, localizing where fidelity breaks down. This is a first step towards interventions that move user simulations closer to faithful renderings of diverse and variable linguistic outputs.

Problem

• user simulation
• persona fidelity
• sociolinguistics
• stylometry
• agentic systems

Innovation

• user simulation
• sociolinguistic persona
• stylometry
• fidelity measurement
• authorship verification