Factual and Informative Review Generation for Explainable Recommendation. (arXiv:2209.12613v2 [cs.CL] UPDATED)

Recent models can generate fluent and grammatical synthetic reviews while
accurately predicting user ratings. The generated reviews, expressing users'
estimated opinions towards related products, are often viewed as natural
language 'rationales' for the jointly predicted rating. However, previous
studies found that existing models often generate repetitive, universally
applicable, and generic explanations, resulting in uninformative rationales.
Further, our analysis shows that previous models' generated content often
contain factual hallucinations. These issues call for novel solutions that
could generate both informative and …

arxiv recommendation review