AI RESEARCH
Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
arXiv CS.LG
•
ArXi:2504.12988v5 Announce Type: replace Existing Learning-to-Defer (L2D) frameworks are limited to single-expert deferral, forcing each query to rely on only one expert and preventing the use of collective expertise. We