← all papers · overview

Updating Parametric Knowledge With Context Distillation Retains Post-training Capabilities

Abstract

Post-training endows pretrained LLMs with a variety of desirable skills, including instruction-following, reasoning, and others. However, these post-trained LLMs only encode knowledge up to a cut-off date, necessitating continual adaptation. Unfortunately, existing solutions cannot simultaneously learn new knowledge from an adaptation document corpora and mitigate the forgetting of earlier learned

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).