← Back to all news
arXiv AI By Dongding Lin, Jian Wang, Xiaoyan Zhao, Wenjie Li

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

Read the original on arXiv AI →

Re2A is a new framework for situated conversational recommendation that models user interactions within shared physical environments. It introduces rubric-based preference reasoning to explicitly capture user preferences from dialogue history and scene context, and a preference-conditioned optimization to align generated responses with both user satisfaction and situational consistency. Experiments on two SCR datasets show that Re2A outperforms existing methods, providing more precise and context-aware recommendations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 2

Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search

The paper introduces DREAMS, a tree‑structured framework for modeling conversational context in Conversational Recommendation Systems. DREAMS uses two node types: elicitation nodes that apply Monte Carlo Tree Search to explore dialogue actions and infer user preferences, and exploitation nodes that refine the inferred preferences with large language models to generate structured retrieval queries. Experiments on benchmark datasets show that DREAMS effectively tracks preference evolution and improves recommendation performance.

By Jincheng Zhang, Chen Huang, Wenqiang Lei, See-Kiong Ng, Yang Deng
llmsbenchmarks
More like this →
arXiv AI
Sep 18

FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System

FacetCRS is a conversational recommender system that tackles the filter‑bubble problem by learning multi‑faceted user preferences—entity, word, context, and review facets—through natural language interactions. The framework adaptively models these preference facets and incorporates external knowledge to provide diverse recommendations. Experiments on two benchmark datasets show that FacetCRS outperforms existing methods in reducing filter bubbles and improving recommendation quality.

By Yongsen Zheng, Ziliang Chen, Jinghui Qin, Liang Lin
benchmarks
More like this →
arXiv AI
Sep 11

PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations

PRAGMA is a benchmark designed to evaluate personalized guidance in long‑term conversations. It includes curated longitudinal conversation histories, evidence annotations, and guidance scenarios that reflect evolving user contexts and incorrect assumptions. Experiments show that current retrieval, memory, and long‑context models struggle to recover relevant conversational evidence and to use it effectively for personalized guidance.

By Hyojeong Yu, Hyukhun Koh, Minsung Kim, Yunah Jang, Kyomin Jung
llmsbenchmarkssafety
More like this →
arXiv AI
Aug 10

Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation

arXiv:2608. 06632v1 Announce Type: new Abstract: Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.

By Ziyun Xu, Bosen Ding, Yue Zhang, Ji Qi, Qingyuan Song, Jizhou Huang, Liwei Wang, Jefferey Santelli, Yue Weng, Qichao Que, Zhenheng Yang, Junfeng Pan, Linhong Zhu
llmsagentsreinforcement-learningefficiencymultimodalsafety
More like this →