auto-regressive-training

Tag

Cards List
#auto-regressive-training

KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training

arXiv cs.CL · yesterday Cached

KItCAT introduces a lightweight training strategy for auto-regressive LLMs that uses input corruption to generate diverse training inputs, improving knowledge injection from niche documents without costly paraphrasing.

0 favorites 0 likes
← Back to home

Submit Feedback