VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelity
This work addresses the need for realistic victim simulations in public service training, representing an incremental improvement by combining existing techniques like GANs and prompting for a specific application.
The paper tackled the problem of simulating victims for scenario-based training by developing VicSim, a model that integrates scenario-based victim modeling with GAN-based training and key-information-based prompting to enhance realism in informational faithfulness, emotional dynamics, and language style. The result showed that VicSim outperformed GPT-4 in human-likeness according to human rater evaluations.
Scenario-based training has been widely adopted in many public service sectors. Recent advancements in Large Language Models (LLMs) have shown promise in simulating diverse personas to create these training scenarios. However, little is known about how LLMs can be developed to simulate victims for scenario-based training purposes. In this paper, we introduce VicSim (victim simulator), a novel model that addresses three key dimensions of user simulation: informational faithfulness, emotional dynamics, and language style (e.g., grammar usage). We pioneer the integration of scenario-based victim modeling with GAN-based training workflow and key-information-based prompting, aiming to enhance the realism of simulated victims. Our adversarial training approach teaches the discriminator to recognize grammar and emotional cues as reliable indicators of synthetic content. According to evaluations by human raters, the VicSim model outperforms GPT-4 in terms of human-likeness.