# Re2A: Situated Conversational Recommendation via Rubric-based Preference Reasoning and Alignment

arXiv: https://arxiv.org/abs/2609.18249 · HTML: https://mlsanity.com/paper/2609.18249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [Direct Preference Optimization with an Offset](https://mlsanity.com/paper/2402.10571/) (2024)
- [A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models](https://mlsanity.com/paper/2405.09589/) (2024)
- [SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations](https://mlsanity.com/paper/2104.08667/) (2021)
- [Evaluating Large Language Models as Generative User Simulators for Conversational Recommendation](https://mlsanity.com/paper/2403.09738/) (2024)
- [Core Knowledge Deficits in Multi-Modal Language Models](https://mlsanity.com/paper/2410.10855/) (2024)
- [Situated and Interactive Multimodal Conversations](https://mlsanity.com/paper/2006.01460/) (2020)
- [MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation](https://mlsanity.com/paper/2502.11903/) (2025)
- [Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models](https://mlsanity.com/paper/2502.16033/) (2025)
- [Fine-Tuning Language Models with Reward Learning on Policy](https://mlsanity.com/paper/2403.19279/) (2024)
- [TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues](https://mlsanity.com/paper/2503.09511/) (2025)
- [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)
- [Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation](https://mlsanity.com/paper/2604.20749/) (2026)

## Abstract (arXiv)

Real-world recommendation scenarios are commonly grounded in shared physical environments during user-recommender interactions. This motivates situated conversational recommendation (SCR), a complex task requiring recommender assistants to jointly reason over dialogue history, co-observed scenes, and in-scene item attributes. However, current approaches struggle with this setting due to two intertwined challenges: accurately understanding situated user preferences throughout the conversation and generating responses that simultaneously satisfy user needs and grounded situations. To this end, we propose Re2A, a framework that formulates SCR as a structured reason-then-align process. We introduce rubric-based preference reasoning, which uses automated rubrics to guide the model toward producing explicit preference states. Based on these states, we propose a preference-conditioned optimization to align response generation with dual objectives: user preference satisfaction and situation consistency. Extensive experiments on two SCR datasets demonstrate that Re2A consistently outperforms state-of-the-art methods, delivering more precise, context-aware conversational recommendations. Our code is available at https://github.com/DongdingLin/Re2A.