Search Results for author:
Found 2 papers, 1 papers with code
Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
When conducting continual learning based on a publicly-released LLM checkpoint, the availability of the original training data may be non-existent.
Response Enhanced Semi-supervised Dialogue Query Generation
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
