GUIDER: Uncertainty Guided Dynamic Re-ranking for Large Language Models Based Recommender Systems
Cai Xu, Xujing Wang, Ziyu Guan, Wei Zhao, Meng Yan
Abstract
Large Language Models (LLMs) are increasingly integral to recommendation systems, offering sophisticated language understanding and generation capabilities. However, their practical application is often hindered by challenges such as data sparsity, the generation of unreliable or hallucinated recommendations, and a general lack of transparency in their decision-making processes. Existing mitigation strategies frequently introduce significant complexity or computational overhead. To address these limitations, particularly the critical gap in quantifying the confidence of LLM-generated recommendations, we propose GUIDER: Uncertainty Guided Dynamic Re-ranking for Large Language Models based Recommender Systems. This new framework innovatively leverages the logits produced by LLMs as evidence for recommended items. By employing a Dirichlet distribution, GUIDER decomposes the total predictive uncertainty into distinct Data Uncertainty (DU), reflecting inherent data ambiguity, and Model Uncertainty (MU), indicating the model
BibTeX
@inproceedings{aaai2026_guideruncertaint,
title = {GUIDER: Uncertainty Guided Dynamic Re-ranking for Large Language Models Based Recommender Systems},
author = {Cai Xu and Xujing Wang and Ziyu Guan and Wei Zhao and Meng Yan},
booktitle = {AAAI 2026},
year = {2026}
}