101 citations · 203 across the 15 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning
Shuhe Wang, Guoyin Wang, Yizhong Wang +3
Packing, initially utilized in the pre-training phase, is an optimization technique designed to maximize hardware resource efficiency by combining different training sequences to f…
cs.LG2023
Are Human-generated Demonstrations Necessary for In-context Learning?
Rui Li, Guoyin Wang, Jiwei Li
Despite the promising few-shot ability of large language models (LLMs), the standard paradigm of In-context Learning (ICL) suffers the disadvantages of susceptibility to selected d…