EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Moral Association Graph: A Cognitive Model for Automated Moral Inference

Aida Ramezani iD, Yang Xu

Topics in Cognitive Science · 2025

DOI: 10.1111/tops.12774 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Topics in Cognitive Science, 2025. Verfasst von Aida Ramezani und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Toronto. Hauptthemen laut MEDLINE: Morals, Artificial Intelligence, Models, Psychological, Cognition. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated moral inference is an emerging topic of critical importance in artificial intelligence. The contemporary approach typically relies on language models to infer moral relevance or moral properties of a concept. This approach demands complex parameterization and costly computation, and it tends to disconnect with existing psychological accounts of moralization. We present a simple cognitive model for moral inference, Moral Association Graph (MAG) , inspired by psychological work on moralization. Our model builds on word association network for inferring moral relevance and draws on rich psychological data. We demonstrate that MAG performs competitively to state‐of‐the‐art language models when evaluated against a comprehensive set of data for automated inference of moral norms and moral judgment of concepts, and in‐context moral inference. We also show that our model yields interpretable outputs and is applicable to informing short‐term moral change.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MoralsArtificial IntelligenceModels, PsychologicalCognitionHumans

Stichwörter der Autor:innen

Artificial intelligenceLanguage modelMoral inferenceMoralizationWord association

Autor:innen und Institutionen

  • Department of Computer Science, University of Toronto.
  • Cognitive Science Program, University of Toronto.

ORCID-Profile: Aida Ramezani

Zitieren

APA

Ramezani, A., & Xu, Y. (2025). Moral Association Graph: A Cognitive Model for Automated Moral Inference. Topics in Cognitive Science. https://doi.org/10.1111/tops.12774

Vancouver

Ramezani A, Xu Y. Moral Association Graph: A Cognitive Model for Automated Moral Inference. Topics in Cognitive Science. 2025. doi:10.1111/tops.12774

BibTeX
@article{Ramezani2025,
  author = {Ramezani, Aida and Xu, Yang},
  title = {Moral Association Graph: A Cognitive Model for Automated Moral Inference},
  journal = {Topics in Cognitive Science},
  year = {2025},
  doi = {10.1111/tops.12774}
}
Kostenlos starten →