Work

Automating the process of selecting countermeasures through multi-criteria decision analysis with large language models

Year: 2026

Type: article

Abstract: The escalating spread of fake news threatens societal trust, institutional stability, and public safety. Law Enforcement Agencies must respond swiftly to disinformation but face severe constraints in time, expertise, and resources. This paper presents an artificial intelligence-based decision-support tool that applies multi-criteria decision analysis through the analytic hierarchy process, combined with large language models, to evaluate disinformation cases and rank context-sensitive, operationally feasible countermeasures defined by experts. Evaluations with Law Enforcement Agencies in the European FERMI project produced highly rated and robust recommendations across diverse scenarios, demonstrating strong alignment with strategic and operational needs. By automating a complex, traditionally manual task and implementing it to form a decision model, the proposed approach enables scalable, sustainable decision-making to combat digital disinformation in high-stakes, resource-constrained environments.

Source: Discover Artificial Intelligence

DOI: 10.1007/s44163-026-00910-3

Authors: Eduardo Noronha, João Varela da Costa, Miguel Mira daSilva

Institutions: University of Lisbon, Instituto de Novas Tecnologias, Institute for Systems Engineering and Computers, Instituto Superior Técnico

Language: English

Topic: Misinformation and Its Impacts

Subfield: Sociology and Political Science

Field: Social Sciences

Domain: Social Sciences

SDG: Peace, justice, and strong institutions

Open Access status: gold

Estimated APC paid: $1,590