arxiv:2601.18777
Abhishek Divekar
adivekar
ยท
AI & ML interests
Synthetic Dataset Generation, LLM-as-a-Judge, Responsible AI
Recent Activity
submitted a paper 1 day ago
When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges authored a paper 3 months ago
PRECISE: Reducing the Bias of LLM Evaluations Using Prediction-Powered Ranking EstimationOrganizations
