Modeling shopper interest broadness with entropy-driven dialogue policy in the context of arbitrarily large product catalogs
This work addresses the problem of efficient user interaction in e-commerce for developers of conversational AI systems, though it is incremental as it builds on existing retrieval and LLM methods.
The paper tackled the challenge of balancing exploration and exploitation in conversational recommender systems with large product catalogs by modeling user interest breadth using entropy of retrieval score distributions, resulting in a method that dynamically routes dialogue policies to improve interactions without bloating context windows.
Conversational recommender systems promise rich interactions for e-commerce, but balancing exploration (clarifying user needs) and exploitation (making recommendations) remains challenging, especially when deploying large language models (LLMs) with vast product catalogs. We address this challenge by modeling the breadth of user interest via the entropy of retrieval score distributions. Our method uses a neural retriever to fetch relevant items for a user query and computes the entropy of the re-ranked scores to dynamically route the dialogue policy: low-entropy (specific) queries trigger direct recommendations, whereas high-entropy (ambiguous) queries prompt exploratory questions. This simple yet effective strategy allows an LLM-driven agent to remain aware of an arbitrarily large catalog in real-time without bloating its context window.