Improving Conversational Recommendation with Contextual Adaptation of External Recommenders and LLM-based Reranking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Chuang, Liang, Weida, Hu, Hengchang, Ng, See-Kiong, Kan, Min-Yen, Li, Haizhou, Deng, Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915897751371776
author Li, Chuang
Liang, Weida
Hu, Hengchang
Ng, See-Kiong
Kan, Min-Yen
Li, Haizhou
Deng, Yang
author_facet Li, Chuang
Liang, Weida
Hu, Hengchang
Ng, See-Kiong
Kan, Min-Yen
Li, Haizhou
Deng, Yang
contents We tackle the challenge of integrating large language models (LLMs) with external recommender systems to enhance domain expertise in conversational recommendation (CRS). Current LLM-based CRS approaches primarily rely on zero/few-shot methods for generating item recommendations based on user queries, but this method faces two significant challenges: (1) without domain-specific adaptation, LLMs frequently recommend items not in the target item space, resulting in low recommendation accuracy; and (2) LLMs largely rely on dialogue context for content-based recommendations, neglecting the collaborative relationships among item sequences. To address these limitations, we introduce the CARE (Contextual Adaptation of Recommenders) framework. CARE (a) integrates external recommender systems as domain experts, producing candidate items through entity-level insights, and (b) customizes LLMs as rerankers to enhance the accuracy by leveraging contextual information. Our results demonstrate that incorporating CARE framework significantly enhances recommendation accuracy of LLMs by an average of 54% and 25% for ReDial and INSPIRED datasets. The most effective CARE strategy involves LLMs selecting and reranking candidate items that external recommenders provide based on contextual insights.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13889
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Conversational Recommendation with Contextual Adaptation of External Recommenders and LLM-based Reranking
Li, Chuang
Liang, Weida
Hu, Hengchang
Ng, See-Kiong
Kan, Min-Yen
Li, Haizhou
Deng, Yang
Information Retrieval
We tackle the challenge of integrating large language models (LLMs) with external recommender systems to enhance domain expertise in conversational recommendation (CRS). Current LLM-based CRS approaches primarily rely on zero/few-shot methods for generating item recommendations based on user queries, but this method faces two significant challenges: (1) without domain-specific adaptation, LLMs frequently recommend items not in the target item space, resulting in low recommendation accuracy; and (2) LLMs largely rely on dialogue context for content-based recommendations, neglecting the collaborative relationships among item sequences. To address these limitations, we introduce the CARE (Contextual Adaptation of Recommenders) framework. CARE (a) integrates external recommender systems as domain experts, producing candidate items through entity-level insights, and (b) customizes LLMs as rerankers to enhance the accuracy by leveraging contextual information. Our results demonstrate that incorporating CARE framework significantly enhances recommendation accuracy of LLMs by an average of 54% and 25% for ReDial and INSPIRED datasets. The most effective CARE strategy involves LLMs selecting and reranking candidate items that external recommenders provide based on contextual insights.
title Improving Conversational Recommendation with Contextual Adaptation of External Recommenders and LLM-based Reranking
topic Information Retrieval
url https://arxiv.org/abs/2508.13889