Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning
Twin Worlds (TW), a framework for improving reliability in knowledge-intensive reasoning through equivariance-based abstention, is proposed, which identifies when answers are not reliably grounded in the provided evidence and outperforms uncertainty- and sufficiency-based baselines.
Vy Nguyen, Ziqi Xu, Jeffrey Chan et al.
· 0 citations