Abishethvarman, V., Chandna, B., Jalan, P., & Naseem, U. (2025). XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content.
Style de citation Chicago (17e éd.)Abishethvarman, Vadivel, Bhavik Chandna, Pratik Jalan, et Usman Naseem. XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content. 2025.
Style de citation MLA (9e éd.)Abishethvarman, Vadivel, et al. XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content. 2025.
Attention : ces citations peuvent ne pas être correctes à 100%.