all AI news
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
March 13, 2024, 4:47 a.m. | Akshat Gupta, Gopala Anumanchipalli
cs.CL updates on arXiv.org arxiv.org
Abstract: Recent work on model editing using Rank-One Model Editing (ROME), a popular model editing method, has shown that there are certain facts that the algorithm is unable to edit without breaking the model. Such edits have previously been called disabling edits. These disabling edits cause immediate model collapse and limits the use of ROME for sequential editing. In this paper, we make two main contributions. Firstly, we show that model collapse with ROME only happens …
abstract algorithm arxiv breaking cs.ai cs.cl edit editing facts model collapse one model popular the algorithm type work
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne