Encode Once, Answer Many: Internalizing Context via Parametric Flow
On document question answering, CLIK substantially improves over the no-context base model and outperforms existing hypernetwork-based generators, while remaining behind a base model that reads the context directly, and it carries over to multi-turn dialogue without any multi-turn-specific training.
Xin-Hao Zhong, Meng-Xuan Wu, Chong-Hua Liao et al.
· 0 citations