Research
Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems
arXiv:2608.19549v1 Announce Type: new Abstract: This paper addresses the issue of the significant labor required to test interview dialogue systems. While interview dialogue systems are expected to be
arXiv:2608.19549v1 Announce Type: new Abstract: This paper addresses the issue of the significant labor required to test interview dialogue systems. While interview dialogue systems are expected to be useful in various scenarios, like other dialogue systems, testing them with human users requires significant effort and cost. Therefore, testing with user simulators can be beneficial. Since most conventional user simulators have been primarily designed for training task-oriented dialogue systems, little attention has been paid to the personas of the simulated users. During development, testing interview dialogue systems requires simulating a wide range of user behaviors, but manually creating a large number of personas is labor-intensive. We propose a method that automatically generates personas for user simulators using a large language model. Furthermore, by assigning personality traits related to communication styles when generating personas, we aim to increase the diversity of communication styles in the user simulator. Experimental results show that the proposed method enables the user simulator to generate utterances with greater variation.
Related
- DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation
- How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue
- Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
Source: arXiv cs.CL | 2026-08-21