Comparing Optimization Targets for Contrast-Consistent Search

1 November 2023

Papers citing "Comparing Optimization Targets for Contrast-Consistent Search"

3 / 3 papers shown

Title
Challenges with unsupervised LLM knowledge discovery Sebastian Farquhar Vikrant Varma Zachary Kenton Johannes Gasteiger Vladimir Mikulik Rohin Shah 43 23 0 15 Dec 2023
Unsupervised Contrast-Consistent Ranking with Language Models Niklas Stoehr Pengxiang Cheng Jing Wang Daniel Preotiuc-Pietro Rajarshi Bhowmik ALM 31 11 0 13 Sep 2023
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Kevin Wang Alexandre Variengien Arthur Conmy Buck Shlegeris Jacob Steinhardt 212 507 0 01 Nov 2022