OpinionConv: Conversational Product Search with Grounded Opinions

TL;DR

OpinionConv introduces a novel conversational AI that leverages real product reviews to generate realistic sales conversations grounded in authentic opinions, enhancing decision-making and user experience.

Contribution

It is the first to ground conversational AI in real opinions from reviews for sales dialogue simulation, improving realism and informativeness.

Findings

Generated opinions are perceived as realistic by users.

Opinions significantly aid decision-making in conversations.

User studies confirm the effectiveness of grounded opinions.

Abstract

When searching for products, the opinions of others play an important role in making informed decisions. Subjective experiences about a product can be a valuable source of information. This is also true in sales conversations, where a customer and a sales assistant exchange facts and opinions about products. However, training an AI for such conversations is complicated by the fact that language models do not possess authentic opinions for their lack of real-world experience. We address this problem by leveraging product reviews as a rich source of product opinions to ground conversational AI in true subjective narratives. With OpinionConv, we develop the first conversational AI for simulating sales conversations. To validate the generated conversations, we conduct several user studies showing that the generated opinions are perceived as realistic. Our assessors also confirm the importance of opinions as an informative basis for decision-making.