MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanation

Abstract

Jackson Trager, Francielle Vargas, Diego Alves, Matteo Guida, Mikel K. Ngueajio, Ameeta Agrawal, Yalda Daryani, Farzan Karimi Malekabadi, Flor Miriam Plaza-del-Arco. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

Authors 8

1. Jackson P. Trager

   University of Southern California

   Affiliation as printed

   University of Southern California

2. Francielle Vargas

   Universidade Estadual Paulista (Unesp)

   Affiliation as printed

   São Paulo State University

3. Diego Alves

   Saarland University

   Affiliation as printed

   Saarland University

4. Mikel K. Ngueajio Aachen

   University of Southern California · Leiden University · Howard University

   Affiliation as printed

   Howard University

   University of Southern California Flor Miriam Plaza-del-Arco Leiden University

5. Ameeta Agrawal

   Portland State University

   Affiliation as printed

   Portland State University

6. Yalda Daryani

   The University of Melbourne

   Affiliation as printed

   University of Melbourne

7. Farzan Karimi Malekabadi
8. Flor Miriam Plaza-del-Arco