Autoregressive ArcaneQA skews to seen data while discriminative Pangu generalizes

ysu_nlp · x · 2026-09-24

Follow-up evidence for the ACL'23 argument: autoregressive ArcaneQA's output distribution skews heavily toward seen data, causing distributional mismatch and generalization failure from seen to unseen, while discriminative Pangu shows much better-aligned output probability distributions over seen and unseen inputs.

Related event: ACL'23 Distinguished Paper: Discriminative Models May Generalize Better Than Autoregressive Ones(3 posts)→

Original post →

More from Research

Research channel →