发表机构
Gaoling School of Artificial Intelligence, Renmin University of China; Faculty of Computer Science, Dalhousie University（中国人民大学高瓴人工智能学院; 达尔豪斯大学计算机科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CRAMER是一种通过请求感知掩码调制冻结骨干参数的推荐控制框架，在多个大规模数据集上优于现有基线，开销最小且可控性与跨域适配能力更强，为请求感知序列推荐建立了新范式。
AI 中文摘要
序列推荐模型功能强大，但在响应用户即时请求方面灵活性有限，难以将推荐内容适配到用户的实时兴趣。遗憾的是，现有的用户请求适配方法往往会带来高昂的计算开销，原因要么是1）对整个骨干网络进行重新训练，要么是2）利用大语言模型的推理能力（即提示工程），这限制了它们在大规模推荐服务中的适用性。本文提出了Control via Request-Aware Masking for Editing Recommenders（CRAMER），这是一个可利用用户自然语言请求即时改变序列推荐模型行为的框架。具体而言，受模型控制理论启发，CRAMER将用户请求视为控制信号，通过掩码来调制冻结的骨干网络参数，在避免昂贵的重新训练的同时实现对多样化请求的即时适配。在多个大规模基准数据集上的实验表明，CRAMER在多个推荐指标上优于四个最先进的请求感知基线，同时实现了最小的开销。此外，所提出的框架还表现出更强的可控性和跨域适配能力，为请求感知序列推荐建立了新的范式。
英文摘要
Sequential recommendation models, while powerful, have limited flexibility in responding to immediate user requests, making it difficult to adapt their recommendations to the user's timely interests. Unfortunately, existing user request adaptation methods often incur high computational overhead due to either 1) retraining the entire backbone network or 2) leveraging the inference ability of large language models (a.k.a. prompt engineering), limiting their applicability in large-scale recommendation services. This paper presents Control via Request-Aware Masking for Editing Recommenders (CRAMER), a framework that takes users' natural-language requests to immediately change sequential recommendation models' behavior. Specifically, inspired by the model control theory, CRAMER treats user requests as control signals to modulate frozen backbone parameters through masking, achieving instant adaptation to diverse requests while avoiding costly retraining. Experiments on multiple large-scale benchmark datasets show that CRAMER outperforms four state-of-the-art request-aware baselines across multiple recommendation metrics while achieving minimal overhead. Moreover, the proposed framework exhibits enhanced controllability and cross-domain adaptability, establishing a new paradigm for request-aware sequential recommendation.
CommentsAccepted by ICML 2026
