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

arXiv: https://arxiv.org/abs/2604.20749 · HTML: https://mlsanity.com/paper/2604.20749/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in LLM reasoning for recommendation, one of 17 directions in LLM reasoning.
- Builds on 5 of its 40 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

- LLM reasoning / [LLM reasoning for recommendation](https://mlsanity.com/lr/llm-reasoning-for-recommendation/)
- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 5 of 5)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [MuMA-ToM: Multi-modal Multi-Agent Theory of Mind](https://mlsanity.com/paper/2408.12574/) (2024)
- [RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models](https://mlsanity.com/paper/2110.07477/) (2021)
- [Muse: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles](https://mlsanity.com/paper/2412.18416/) (2024)
- [ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems](https://mlsanity.com/paper/2509.21371/) (2025)

## Built on by (most cited first, 1 of 1)

- [Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignment](https://mlsanity.com/paper/2609.18249/) (2026)

## Abstract (arXiv)

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.