Sanket Badhe

LLMs are poised to revolutionize online abuse detection, but realizing their potential requires tackling critical challenges like latency, cost, and adversarial attacks across the entire abuse detection lifecycle.

Forget fine-tuning: Prompt-Level Distillation lets small models match frontier reasoning performance by distilling explicit reasoning patterns into structured system prompts.

LLMs still struggle with infrequently occurring knowledge, and this paper provides a structured framework to understand why, how we can fix it, and what the implications are for responsible AI.