Are PPO-ed Language Models Hackable?

28 May 2024

Papers citing "Are PPO-ed Language Models Hackable?"

3 / 3 papers shown

Title
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity Andrew Lee Xiaoyan Bai Itamar Pres Martin Wattenberg Jonathan K. Kummerfeld Rada Mihalcea 64 95 0 03 Jan 2024
The Pile: An 800GB Dataset of Diverse Text for Language Modeling Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe ... Horace He Anish Thite Noa Nabeshima Shawn Presser Connor Leahy AIMat 245 1,986 0 31 Dec 2020
The Woman Worked as a Babysitter: On Biases in Language Generation Emily Sheng Kai-Wei Chang Premkumar Natarajan Nanyun Peng 206 615 0 03 Sep 2019