We invited Lisa Li to talk about her recent work, Prefix-Tuning: Optimizing Continuous Prompts for Generation. Prefix tuning is a lightweight alternative to finetuning, and the idea is to tune only a fixed-length task-specific continuous vector, and to keep the pretrained transformer parameters frozen. We discussed how prefix tuning compares with finetuning and other efficient alternatives on two tasks in various experimental settings, and in what scenarios prefix tuning is preferable.
Lisa is a Phd student at Stanford University. Lisa's webpage: https://xiangli1999.github.io/
The hosts for this episode are Pradeep Dasigi and Ana Marasović.
Podden och tillhörande omslagsbild på den här sidan tillhör
Allen Institute for Artificial Intelligence. Innehållet i podden är skapat av Allen Institute for Artificial Intelligence och inte av,
eller tillsammans med, Poddtoppen.