用自然语言检索用户行为，让大模型更懂推荐。
LLMs as Better Recommenders with Natural Language Collaborative Signals: A Self-Assessing Retrieval Approach
- 用自然语言直接表达用户行为，对齐大模型语义空间
- 自评估重排器让大模型自己判断哪些行为有用
- 适合想提升大模型推荐效果的研究者和工程师
有效融合协同信息（CI）是利用大语言模型进行推荐的关键。现有方法多采用软标记或抽象标识符编码CI，与大模型的自然语言预训练存在语义错位，影响知识整合。为此，我们提出直接以自然语言形式表达CI，更好契合大模型的语义空间。通过检索一组最相关的用户行为自然语言描述实现。但如何识别有信息量的CI仍具挑战，因相似性与实用性评估复杂。为此，我们提出自评估协同检索框架SCORE，遵循检索-重排范式：首先构建协同检索器（CAR），同时考虑协同模式与语义相似性；然后设计自评估重排器（SARE），利用大模型自身推理能力评估并排序检索到的行为；最后将选定行为作为自然语言CI前缀加入大模型提示中以指导推荐。在两个公开数据集上的大量实验验证了SCORE在提升大模型推荐效果方面的有效性。
原文摘要 · Abstract (English)
Incorporating collaborative information (CI) effectively is crucial for leveraging LLMs in recommendation tasks. Existing approaches often encode CI using soft tokens or abstract identifiers, which introduces a semantic misalignment with the LLM's natural language pretraining and hampers knowledge integration. To address this, we propose expressing CI directly in natural language to better align with LLMs' semantic space. We achieve this by retrieving a curated set of the most relevant user behaviors in natural language form. However, identifying informative CI is challenging due to the complexity of similarity and utility assessment. To tackle this, we introduce a Self-assessing COllaborative REtrieval framework (SCORE) following the retrieve-rerank paradigm. First, a Collaborative Retriever (CAR) is developed to consider both collaborative patterns and semantic similarity. Then, a Self-assessing Reranker (SARE) leverages LLMs' own reasoning to assess and prioritize retrieved behaviors. Finally, the selected behaviors are prepended to the LLM prompt as natural-language CI to guide recommendation. Extensive experiments on two public datasets validate the effectiveness of SCORE in improving LLM-based recommendation.
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。