Rehman, Mohammad Zia Ur, et al. “X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and a Novel LLM-Consulted Explanation Framework”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 46, Mar. 2026, pp. 39134-42, doi:10.1609/aaai.v40i46.41261.