A Jury, Not an Electorate: Label-Free Reliability Estimation for Ensembles of Language Models
The jury, with nine experts of up to 3B parameters, performs comparably to the same fusion rule with label-fitted weights, showing no statistically significant advantage from supervision, and outperforms the best single model with matched self-consistency and the strongest label-free alternative on the full benchmark.
A. Rozza, D. Mambelli, S. Motta et al.
· 0 citations