Verifiable Reasoning for LLM-based Generative Recommendation
Xinyu Lin, Hanqing Zeng, Hanchao Yu, Yinglong Xia, Jiang Zhang, Aashu Singh, Fei Liu, Wenjie Wang, Fuli Feng, Tat-Seng Chua, Qifan Wang

TL;DR
This paper introduces a verifiable reasoning framework for LLM-based recommendations, interleaving reasoning with verification to improve accuracy and reliability in understanding user preferences.
Contribution
It proposes the reason-verify-recommend paradigm and the VRec model, enabling multi-dimensional verification to enhance recommendation quality.
Findings
VRec significantly improves recommendation accuracy.
The approach enhances scalability and efficiency.
Verification guides reasoning to better capture user preferences.
Abstract
Reasoning in Large Language Models (LLMs) has recently shown strong potential in enhancing generative recommendation through deep understanding of complex user preference. Existing approaches follow a {reason-then-recommend} paradigm, where LLMs perform step-by-step reasoning before item generation. However, this paradigm inevitably suffers from reasoning degradation (i.e., homogeneous or error-accumulated reasoning) due to the lack of intermediate verification, thus undermining the recommendation. To bridge this gap, we propose a novel \textbf{\textit{reason-verify-recommend}} paradigm, which interleaves reasoning with verification to provide reliable feedback, guiding the reasoning process toward more faithful user preference understanding. To enable effective verification, we establish two key principles for verifier design: 1) reliability ensures accurate evaluation of reasoning…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Recommender Systems and Techniques · Multimodal Machine Learning Applications
