Creating Frameworks and Datasets at the Intersection of AI Safety and Elections
Dmonte, Alphaeus Wang, Yuxia Nakov, Preslav Li, Haonan Han, Xudong Zampieri, Marcos Lybarger, Kevin Albanese, Massimiliano Baldwin, Timothy
Dmonte, Alphaeus
Wang, Yuxia
Nakov, Preslav
Li, Haonan
Han, Xudong
Zampieri, Marcos
Lybarger, Kevin
Albanese, Massimiliano
Baldwin, Timothy
Supervisor
Department
Natural Language Processing
Embargo End Date
Type
Book chapter
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
This chapter explores the intersection of Artificial Intelligence (AI) and elections, focusing on the critical challenge of ensuring safety in the age of Large Language Models (LLMs) including AI-generated misinformation and its impact on electoral integrity. This chapter is divided into two complementary parts. The first part describes Do-Not-Answer, a framework featuring a three-level hierarchical taxonomy of LLM risks including hallucination, bias, toxic language, and misinformation. Do-Not-Answer has been used to create datasets in multiple languages that serve to evaluate LLMs with respect to mitigation strategies, content filtering, and model alignment. The second part discusses the ElectAI taxonomy and dataset. ElectAI has been created to aid claim understanding with respect to election processes, equipment, and claims of fraud in both AI- and human-generated social media posts. The two parts combined present the reader with a comprehensive overview of both general and election-related AI safety issues along with strategies to address them.
Citation
A. Dmonte et al., “Creating Frameworks and Datasets at the Intersection of AI Safety and Elections,” PROMISE – PROMoting AI’s Safe usage for Elections, pp. 115–145, 2025, doi: 10.1007/978-3-031-89853-2_9.
Source
PROMISE – PROMoting AI’s Safe usage for Elections
Conference
Keywords
Subjects
Source
Publisher
Springer Nature