Preprint
Aug 2026
When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs
This version reports that the most natural repair also fails, and separates three signal failures that v1 treated as one, and reports that on hosted serverless inference at a small budget, three reasoning-native models could not be evaluated, for three separately measured reasons.
Utkarsh Bahuguna
· 2 citations
· ⚡2