Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913863140638720 |
|---|---|
| author | Zeng, Donghuo Legaspi, Roberto Sun, Yuewen Dong, Xinshuai Ikeda, Kazushi Spirtes, Peter Zhang, Kun |
| author_facet | Zeng, Donghuo Legaspi, Roberto Sun, Yuewen Dong, Xinshuai Ikeda, Kazushi Spirtes, Peter Zhang, Kun |
| contents | We hypothesize that optimal system responses emerge from adaptive strategies grounded in causal and counterfactual knowledge. Counterfactual inference allows us to create hypothetical scenarios to examine the effects of alternative system responses. We enhance this process through causal discovery, which identifies the strategies informed by the underlying causal structure that govern system behaviors. Moreover, we consider the psychological constructs and unobservable noises that might be influencing user-system interactions as latent factors. We show that these factors can be effectively estimated. We employ causal discovery to identify strategy-level causal relationships among user and system utterances, guiding the generation of personalized counterfactual dialogues. We model the user utterance strategies as causal factors, enabling system strategies to be treated as counterfactual actions. Furthermore, we optimize policies for selecting system responses based on counterfactual data. Our results using a real-world dataset on social good demonstrate significant improvements in persuasive system outcomes, with increased cumulative rewards validating the efficacy of causal discovery in guiding personalized counterfactual inference and optimizing dialogue policies for a persuasive dialogue system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13904 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge Zeng, Donghuo Legaspi, Roberto Sun, Yuewen Dong, Xinshuai Ikeda, Kazushi Spirtes, Peter Zhang, Kun Human-Computer Interaction Artificial Intelligence Computation and Language We hypothesize that optimal system responses emerge from adaptive strategies grounded in causal and counterfactual knowledge. Counterfactual inference allows us to create hypothetical scenarios to examine the effects of alternative system responses. We enhance this process through causal discovery, which identifies the strategies informed by the underlying causal structure that govern system behaviors. Moreover, we consider the psychological constructs and unobservable noises that might be influencing user-system interactions as latent factors. We show that these factors can be effectively estimated. We employ causal discovery to identify strategy-level causal relationships among user and system utterances, guiding the generation of personalized counterfactual dialogues. We model the user utterance strategies as causal factors, enabling system strategies to be treated as counterfactual actions. Furthermore, we optimize policies for selecting system responses based on counterfactual data. Our results using a real-world dataset on social good demonstrate significant improvements in persuasive system outcomes, with increased cumulative rewards validating the efficacy of causal discovery in guiding personalized counterfactual inference and optimizing dialogue policies for a persuasive dialogue system. |
| title | Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge |
| topic | Human-Computer Interaction Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2504.13904 |