Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2501.03139 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913637196627968 |
|---|---|
| author | Li, Yerong Liu, Yiren Huang, Yun |
| author_facet | Li, Yerong Liu, Yiren Huang, Yun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_03139 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelity Li, Yerong Liu, Yiren Huang, Yun Computation and Language Human-Computer Interaction 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. |
| title | VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelity |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2501.03139 |