Is He Extroverted? Identifying Missing Relevant Personas for Faithful User Simulation

TL;DR

This paper investigates the importance of identifying missing relevant personas in user simulation to improve dialogue response validity, introducing a new benchmark and evaluation criteria for this task.

Contribution

It presents PICQ-drama, a novel benchmark dataset for identifying missing persona dimensions in user simulation, and evaluates large language models on this task.

Findings

LLMs can identify missing persona dimensions with varying accuracy.

Different persona categories influence user responses distinctly.

The benchmark reveals cognitive differences between LLMs and humans.

Abstract

Existing user simulation approaches focus on generating user-like responses in dialogue. They often assume that the provided persona is sufficient for producing such responses, without verifying whether critical personas are supplied. This raises concerns about the validity of simulation results. To address this issue, we study the task of identifying persona dimensions (e.g., "whether the user is price-sensitive") that are relevant but missing in simulating a user's reply for a given dialogue context. We introduce PICQ-drama (constructed from TVShowGuess), a benchmark of context-aware choice questions, annotated with missing persona dimensions whose absence leads to ambiguous user choices. We further design diverse evaluation criteria for missing persona identification. Benchmarking leading LLMs on our PICQ-drama dataset demonstrates the feasibility of this task. Evaluation across diverse criteria, along with further analyses, reveals cognitive differences between LLMs and humans and highlights the distinct roles of different persona categories in shaping responses.