OpinionConv: Conversational Product Search with Grounded Opinions
This work addresses the challenge of simulating sales conversations for AI, though it is incremental in leveraging existing review data.
The paper tackled the problem of training conversational AI for product search without authentic opinions by grounding it in product reviews, resulting in generated conversations that users perceived as realistic and informative.
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.