ExpCTR jointly trains an LLM explanation generator and a CTR model via two reinforcement rewards, reporting higher AUC than ID-based baselines on BookCrossing, ML-20M, and Amazon Books.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explainable CTR Prediction via LLM Reasoning
ExpCTR jointly trains an LLM explanation generator and a CTR model via two reinforcement rewards, reporting higher AUC than ID-based baselines on BookCrossing, ML-20M, and Amazon Books.