跳到主要导航 跳到搜索 跳到主要内容

Context-Aware Personalized Recommendation Using Large Language Models with Feedback-driven Adaptive Score Calibration

  • Yuanyuan Li
  • , Xin Liu*
  • , Minxia Liu
  • , Jian Xie
  • , Xi Xiang
  • *此作品的通讯作者
  • Beijing Institute of Technology
  • Northwestern Polytechnical University Xian

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

LLM-based recommendation methods lack effective context modeling and lightweight online feedback adaptation, failing to capture dynamic user preferences. This paper proposes a context-aware recommendation framework with feedback-driven adaptive score calibration. We design an attention module to weight multidimensional context signals and capture context-dependent preferences. A gated fusion unit adaptively combines collaborative filtering embeddings and LLM semantic representations to alleviate data sparsity. Moreover, a lightweight calibration module updates only a single scalar parameter using real-time user feedback, avoiding the high computational cost and training instability of reinforcement learning and bandit algorithms. Experiments on MovieLens-1M, Amazon-Books and Yelp demonstrate that our model outperforms mainstream baselines in Precision, Recall and F1. Ablation studies and embedding visualization verify the complementarity of all core modules. The framework balances accuracy and efficiency and is suitable for real-time recommendation scenarios.

源语言英语
主期刊名Proceedings of the 2nd International Conference on Artificial Intelligence and Product Design, AIPD 2026
出版商Association for Computing Machinery, Inc
页570-579
页数10
ISBN(电子版)9798400722707
DOI
出版状态已出版 - 16 9月 2026
已对外发布是
活动2nd International Conference on Artificial Intelligence and Product Design, AIPD 2026 - Nanjing, 中国
期限: 24 4月 2026 → 26 4月 2026

丛书

姓名Proceedings of the 2nd International Conference on Artificial Intelligence and Product Design, AIPD 2026

会议

会议2nd International Conference on Artificial Intelligence and Product Design, AIPD 2026
国家/地区中国
市Nanjing
时期24/04/26 → 26/04/26

学术指纹

探究 'Context-Aware Personalized Recommendation Using Large Language Models with Feedback-driven Adaptive Score Calibration' 的科研主题。它们共同构成独一无二的学术指纹。

引用此