1 code implementation • 2 Mar 2024 • Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, Jinsong Su
When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent.
1 code implementation • 20 Dec 2023 • Jianheng Huang, Ante Wang, Linfeng Gao, Linfeng Song, Jinsong Su
Based on the observation that the search query is typically related to the topic of dialogue response, we train a response-augmented query producer (RA) to provide rich and effective training signals for QP.