Accepted to MTLILM @ NeurIPS 2025 (Spotlight)
Authors: Mrinal Agarwal, Saad Rana, Theo Sundoro, Hermela Berhe
We introduce WOLF (Weighted Online Learning Framework), a novel framework for evaluating large language model robustness in multi-turn conversational settings under adversarial pressure. WOLF systematically tests model responses when users attempt to manipulate, mislead, or extract harmful information through extended dialogue. Our framework provides quantitative metrics for measuring model stability and safety across conversation trajectories.
