An active-learning loop that uses GPT-4o-mini to label the item pairs a classifier is most unsure about boosts out-of-distribution accuracy by up to 37% but barely helps or even hurts in-distribution.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Knowledge-Augmented Relation Learning for Complementary Recommendation with Large Language Models
An active-learning loop that uses GPT-4o-mini to label the item pairs a classifier is most unsure about boosts out-of-distribution accuracy by up to 37% but barely helps or even hurts in-distribution.