1 code implementation • 24 Jul 2023 • Roi Cohen, Eden Biran, Ori Yoran, Amir Globerson, Mor Geva
This has led to the development of various editing methods that allow updating facts encoded by the model.
no code implementations • 22 May 2023 • Roi Cohen, May Hamri, Mor Geva, Amir Globerson
A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability.
no code implementations • 30 Jan 2023 • Roi Cohen, Mor Geva, Jonathan Berant, Amir Globerson
Here, we propose to address this goal by extracting a knowledge-graph of facts from a given language model.