conftrace_

continual knowledge learning

3 papers

Explore in graph

Also known as

CKL

Co-occurring keywords · papers mentioning both

large language model (2) catastrophic forgetting (2) token importance (1) attention augmentation (1) knowledge-intensive task (1) world knowledge (1) retrieval-augmented language model (1) knowledge retention (1) language model pretraining (1) search engine (1)

Papers

Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning NeurIPS 2024 The Web Can Be Your Oyster for Improving Language Models ACL 2023 Towards Continual Knowledge Learning of Language Models ICLR 2022