1. Traditional recommendation systems have limitations in obtaining fine-grained and dynamic user preference.
2. Conversational recommendation system (CRS) enables the system to directly ask users about their preferred attributes on items.
3. This paper proposes a generic framework called Conversational Path Reasoning (CPR) that models conversational recommendation as an interactive path reasoning problem on a graph, utilizing the user preferred attributes in an explicit way.
The article is generally trustworthy and reliable, as it provides evidence for its claims through extensive experiments on two datasets Yelp and LastFM. The authors also provide a detailed description of their proposed method, Conversational Path Reasoning (CPR), which is based on a graph structure that can prune off many irrelevant candidate attributes, leading to better chances of hitting user-preferred attributes. The article does not present any one-sided reporting or unsupported claims, and all the points are well-supported by evidence from the experiments conducted. There are no missing points of consideration or missing evidence for the claims made, and all counterarguments are explored thoroughly. The article does not contain any promotional content or partiality, and possible risks are noted throughout the paper. Both sides of the argument are presented equally, making it a balanced and unbiased piece of research work.