A prompting pipeline and statement-level metrics show that six state-of-the-art text-based explainable recommendation models achieve high semantic similarity but very low factual consistency on Amazon review data.
In: Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2verdicts
UNVERDICTED 2representative citing papers
Curr-RLCER applies curriculum reinforcement learning with coherence-driven rewards to align generated explanations with predicted ratings in explainable recommendation systems.
citing papers explorer
-
On the Factual Consistency of Text-based Explainable Recommendation Models
A prompting pipeline and statement-level metrics show that six state-of-the-art text-based explainable recommendation models achieve high semantic similarity but very low factual consistency on Amazon review data.
-
Curr-RLCER:Curriculum Reinforcement Learning For Coherence Explainable Recommendation
Curr-RLCER applies curriculum reinforcement learning with coherence-driven rewards to align generated explanations with predicted ratings in explainable recommendation systems.