Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jarboui, Firas, Memari, Issa
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.06185
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912575880429568
author Jarboui, Firas
Memari, Issa
author_facet Jarboui, Firas
Memari, Issa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06185
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modeling shopper interest broadness with entropy-driven dialogue policy in the context of arbitrarily large product catalogs
Jarboui, Firas
Memari, Issa
Information Retrieval
Machine Learning
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.
title Modeling shopper interest broadness with entropy-driven dialogue policy in the context of arbitrarily large product catalogs
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2509.06185