Weak-to-strong generalization is nearly inevitable in linear logistic regression for most student-teacher pairs without any model capacity mismatch.
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Trust functions filter unreliable weak labels to enable near-lossless weak-to-strong generalization and iterative chaining.
citing papers explorer
-
Weak-to-Strong Generalization is Nearly Inevitable (in Linear Models)
Weak-to-strong generalization is nearly inevitable in linear logistic regression for most student-teacher pairs without any model capacity mismatch.
-
Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher
Trust functions filter unreliable weak labels to enable near-lossless weak-to-strong generalization and iterative chaining.