From Dialogue to Destination: Geography-Aware Large Language Models with Multimodal Fusion for Conversational Recommendation
Yeming Li, Chenxi Liu, Jie Zou, Cheng Long, Chaoning Zhang, Peng Wang, Yang Yang
Abstract
Conversational Recommender Systems (CRS) aim to provide personalized recommendations by interacting with users through natural language dialogue. However, in scenarios requiring deep geospatial awareness, existing methods, including those based on Large Language Models (LLMs), still face significant challenges in effectively fusing heterogeneous, multimodal geographic information with dynamic dialogue context. Simple fusion strategies struggle to resolve the asymmetric dependencies between dynamic user intent and static geographic context and fail to bridge the semantic gap between LLMs and structured geospatial data. To address these issues, we propose a framework for geography-aware CRS, named GeoCRS. Our core idea is to empower a frozen LLM with powerful geospatial reasoning capabilities by conditioning it on a dynamic, multimodal guidance signal generated by an external fusion architecture, all without altering the LLM
BibTeX
@inproceedings{aaai2026_fromdialoguetode,
title = {From Dialogue to Destination: Geography-Aware Large Language Models with Multimodal Fusion for Conversational Recommendation},
author = {Yeming Li and Chenxi Liu and Jie Zou and Cheng Long and Chaoning Zhang and Peng Wang and Yang Yang},
booktitle = {AAAI 2026},
year = {2026}
}