SOTAVerified

Dialogue Evaluation

Papers

No papers found.

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MDD-EvalSpearman Correlation0.51Unverified
2Lin-Reg (all)Spearman Correlation0.49Unverified
3USRSpearman Correlation0.42Unverified
4USR - DR (x = c)Spearman Correlation0.32Unverified
5USR - MLMSpearman Correlation0.31Unverified
6USR - DR (x = f)Spearman Correlation0.14Unverified
#ModelMetricClaimedVerifiedStatus
1Lin-Reg (all)Spearman Correlation0.54Unverified
2USR - DR (x = c)Spearman Correlation0.48Unverified
3USRSpearman Correlation0.47Unverified
4USR - MLMSpearman Correlation0.08Unverified
5USR - DR (x = f)Spearman Correlation-0.05Unverified