List your company

Dialogue Alignment on Relational Failure Mode Benchmark (test)

0.4116Mean UtilityReranked-best
-0.172256-0.0206780.13090.282478Apr 2, 2026

Evaluation results

MethodLinks
Reranked-beststrategy=utility-based reranking2026.040.41160.2498
Manual-DPO2026.040.34220.1804
SFT-baseline2026.040.1618—
CCN-candidatemode=candidate generation2026.04-0.1498-0.3116