让大模型理解用户偏好强弱，提升推荐精度
Every Preference Has Its Strength: Injecting Ordinal Semantics into LLM-Based Recommenders
- 用文本编码表示不同偏好强度，作为语义锚点
- 在多个数据集上显著优于现有方法，尤其擅长区分细微偏好
- 适合需要精准个性化推荐的场景，如电商、内容平台
近期研究表明，大语言模型（LLM）可通过混合提示整合协同过滤（CF）信号来增强推荐系统。然而，现有大多数CF-LLM框架将显式评分简化为隐式或仅正向反馈，丢失了蕴含细粒度偏好强度的序数结构，导致难以捕捉分级语义和微妙偏好差异。为此，本文提出序数语义锚定（OSA），一种融合协同过滤与大语言模型的新型框架。OSA通过建模交互级别的用户反馈，显式引入偏好强度：将序数偏好等级表示为数值型文本标记，并利用其词元嵌入作为语义锚点，在LLM潜在空间中对齐用户-物品交互表示。通过跨序数层级的强度感知对齐，OSA在融合协同信号时有效保留了偏好语义。在多个真实世界数据集上的实验表明，OSA持续优于现有基线，尤其在成对偏好评估任务中表现突出，验证了其在建模细粒度用户偏好方面相较于以往CF-LLM方法的有效性。
原文摘要 · Abstract (English)
Recent work has shown that large language models (LLMs) can enhance recommender systems by integrating collaborative filtering (CF) signals through hybrid prompting. However, most existing CF-LLM frameworks collapse explicit ratings into implicit or positive-only feedback, discarding the ordinal structure that conveys fine-grained preference strength. As a result, these models struggle to exploit graded semantics and nuanced preference distinctions. We propose Ordinal Semantic Anchoring (OSA), a hybrid CF-LLM framework that explicitly incorporates preference strength by modeling interaction-level user feedback. OSA represents ordinal preference levels as numeric textual tokens and uses their token embeddings as semantic anchors to align user-item interaction representations in the LLM latent space. Through strength-aware alignment across ordinal levels, OSA preserves preference semantics when integrating collaborative signals with LLMs. Experiments on multiple real-world datasets demonstrate that OSA consistently outperforms existing baselines, particularly in pairwise preference evaluation, highlighting its effectiveness in modeling fine-grained user preferences over prior CF-LLM methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。