Megadose AI progress, ranked and analyzed.

Type-Safe Is Not Error-Free: A Constrained Decision Head Follows the Option Name, Not the Rubric Bound to It

· ArXiv · AI/CL/LG ·
Changing option names alone made typed decision models reverse their rankings while still producing valid outputs.

The paper tests Jev and related open-weight models by keeping the task, rubrics, and option set fixed, then swapping which names attach to which rubrics. Moving from neutral labels to semantically loaded `no/yes` labels caused large answer flips, including an AUC drop from .94 to .23 on 1,200 workflow decisions. Random character labels returned the models to the neutral-control regime, pointing to the polarity of the option names rather than renaming itself. The type-error rate stayed at 0%, even when accuracy degraded sharply. ArXiv · AI/CL/LG's note

score 4

Categories: Research