ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2504.13904
26
0

Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge

8 April 2025
Donghuo Zeng
Roberto Legaspi
Yuewen Sun
Xinshuai Dong
Kazushi Ikeda
Peter Spirtes
Anton van den Hengel
    CML
ArXivPDFHTML
Abstract

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.

View on arXiv
@article{zeng2025_2504.13904,
  title={ Generative Framework for Personalized Persuasion: Inferring Causal, Counterfactual, and Latent Knowledge },
  author={ Donghuo Zeng and Roberto Legaspi and Yuewen Sun and Xinshuai Dong and Kazushi Ikeda and Peter Spirtes and Kun Zhang },
  journal={arXiv preprint arXiv:2504.13904},
  year={ 2025 }
}
Comments on this paper