AI RESEARCH
PLR: Plackett-Luce for Reordering In-Context Learning Examples
arXiv CS.LG
•
ArXi:2603.21373v1 Announce Type: new In-context learning (ICL) adapts large language models by conditioning on a small set of ICL examples, avoiding costly parameter updates. Among other factors, performance is often highly sensitive to the ordering of the examples. However, exhaustive search over the $n!$ possible orderings is infeasible. Therefore efficient ordering methods use model confidence measures (e.g., label-probability entropy) over label sets or take a direct approach to finding the best ordering.