all AI news
Updating Language Models with Unstructured Facts: Towards Practical Knowledge Editing
March 1, 2024, 5:49 a.m. | Xiaobao Wu, Liangming Pan, William Yang Wang, Anh Tuan Luu
cs.CL updates on arXiv.org arxiv.org
Abstract: Knowledge editing aims to inject knowledge updates into language models to keep them correct and up-to-date. However, its current evaluation strategies are notably impractical: they solely update with well-curated structured facts (triplets with subjects, relations, and objects), whereas real-world knowledge updates commonly emerge in unstructured texts like news articles. In this paper, we propose a new benchmark, Unstructured Knowledge Editing (UKE). It evaluates editing performance directly using unstructured texts as knowledge updates, termed unstructured facts. …
abstract arxiv cs.ai cs.cl current editing evaluation facts knowledge language language models objects practical relations strategies them type unstructured update updates world
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US