Patel, Oam

3 publications

TMLR 2025 Defending Against Unforeseen Failure Modes with Latent Adversarial Training Stephen Casper, Lennart Schulze, Oam Patel, Dylan Hadfield-Menell

ICLRW 2024 Preventing Memorized Completions Through White-Box Filtering Oam Patel, Rowan Wang

NeurIPS 2023 Inference-Time Intervention: Eliciting Truthful Answers from a Language Model Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg