Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lin, Dongding, Wang, Jian, Li, Yongqi, Li, Wenjie
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908987218198528
author Lin, Dongding
Wang, Jian
Li, Yongqi
Li, Wenjie
author_facet Lin, Dongding
Wang, Jian
Li, Yongqi
Li, Wenjie
contents Situated conversational recommendation (SCR), which utilizes visual scenes grounded in specific environments and natural language dialogue to deliver contextually appropriate recommendations, has emerged as a promising research direction due to its close alignment with real-world scenarios. Compared to traditional recommendations, SCR requires a deeper understanding of dynamic and implicit user preferences, as the surrounding scene often influences users' underlying interests, while both may evolve across conversations. This complexity significantly impacts the timing and relevance of recommendations. To address this, we propose situated preference reasoning (SiPeR), a novel framework that integrates two core mechanisms: (1) Scene transition estimation, which estimates whether the current scene satisfies user needs, and guides the user toward a more suitable scene when necessary; and (2) Bayesian inverse inference, which leverages the likelihood of multimodal large language models (MLLMs) to predict user preferences about candidate items within the scene. Extensive experiments on two representative benchmarks demonstrate SiPeR's superiority in both recommendation accuracy and response generation quality. The code and data are available at https://github.com/DongdingLin/SiPeR.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20749
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
Lin, Dongding
Wang, Jian
Li, Yongqi
Li, Wenjie
Artificial Intelligence
Situated conversational recommendation (SCR), which utilizes visual scenes grounded in specific environments and natural language dialogue to deliver contextually appropriate recommendations, has emerged as a promising research direction due to its close alignment with real-world scenarios. Compared to traditional recommendations, SCR requires a deeper understanding of dynamic and implicit user preferences, as the surrounding scene often influences users' underlying interests, while both may evolve across conversations. This complexity significantly impacts the timing and relevance of recommendations. To address this, we propose situated preference reasoning (SiPeR), a novel framework that integrates two core mechanisms: (1) Scene transition estimation, which estimates whether the current scene satisfies user needs, and guides the user toward a more suitable scene when necessary; and (2) Bayesian inverse inference, which leverages the likelihood of multimodal large language models (MLLMs) to predict user preferences about candidate items within the scene. Extensive experiments on two representative benchmarks demonstrate SiPeR's superiority in both recommendation accuracy and response generation quality. The code and data are available at https://github.com/DongdingLin/SiPeR.
title Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
topic Artificial Intelligence
url https://arxiv.org/abs/2604.20749