Legend: Leveraging Representation Engineering to Annotate Safety Margin
for Preference Datasets

Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets

12 June 2024

Youcheng Huang

Zheng-Wei Zhang

Papers citing "Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets"

4 / 4 papers shown

Title
The Platonic Representation Hypothesis Minyoung Huh Brian Cheung Tongzhou Wang Phillip Isola 72 107 0 13 May 2024
The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models? Qinyu Zhao Ming Xu Kartik Gupta Akshay Asthana Liang Zheng Stephen Gould 23 7 0 14 Mar 2024
Toy Models of Superposition Nelson Elhage Tristan Hume Catherine Olsson Nicholas Schiefer T. Henighan ... Sam McCandlish Jared Kaplan Dario Amodei Martin Wattenberg C. Olah AAML MILM 117 314 0 21 Sep 2022
Fine-Tuning Language Models from Human Preferences Daniel M. Ziegler Nisan Stiennon Jeff Wu Tom B. Brown Alec Radford Dario Amodei Paul Christiano G. Irving ALM 273 1,561 0 18 Sep 2019