AdaRec：基于叙事画像与双通道推理的大语言模型自适应推荐
AdaRec: Adaptive Recommendation with LLMs via Narrative Profiling and Dual-Channel Reasoning
AI总结：
AdaRec 通过叙事画像将用户-物品交互转化为自然语言，并采用水平行为对齐与垂直因果归因的双通道推理，在少样本和零样本推荐中显著超越基线，且轻量微调即可达到全量微调性能。
摘要：
我们提出 AdaRec，一个少样本上下文学习框架，利用大语言模型实现自适应个性化推荐。AdaRec 引入叙事画像（narrative profiling），将用户-物品交互转化为自然语言表示，以实现统一的任务处理并增强人类可读性。以双变量推理范式为核心，AdaRec 采用双通道架构，将水平行为对齐（发现同伴驱动的模式）与垂直因果归因（突出用户偏好背后的决定性因素）相结合。与现有基于大语言模型的方法不同，AdaRec 通过语义表示消除了人工特征工程，并以最少的监督支持快速的跨任务适应。在真实电子商务数据集上的实验表明，在少样本设置下，AdaRec 的性能优于机器学习模型和基于大语言模型的基线方法，提升幅度最高达 8%。在零样本场景下，与专家精心设计的画像相比，其提升幅度最高达 19%，表明其在极少交互数据条件下对长尾个性化推荐的有效性。此外，在 AdaRec 生成的合成数据上进行轻量级微调即可达到与完全微调模型相当的性能，凸显了其在多样化任务中的效率和泛化能力。
英文摘要：
We propose AdaRec, a few-shot in-context learning framework that leverages large language models for an adaptive personalized recommendation. AdaRec introduces narrative profiling, transforming user-item interactions into natural language representations to enable unified task handling and enhance human readability. Centered on a bivariate reasoning paradigm, AdaRec employs a dual-channel architecture that integrates horizontal behavioral alignment, discovering peer-driven patterns, with vertical causal attribution, highlighting decisive factors behind user preferences. Unlike existing LLM-based approaches, AdaRec eliminates manual feature engineering through semantic representations and supports rapid cross-task adaptation with minimal supervision. Experiments on real ecommerce datasets demonstrate that AdaRec outperforms both machine learning models and LLM-based baselines by up to eight percent in few-shot settings. In zero-shot scenarios, it achieves up to a nineteen percent improvement over expert-crafted profiling, showing effectiveness for long-tail personalization with minimal interaction data. Furthermore, lightweight fine-tuning on synthetic data generated by AdaRec matches the performance of fully fine-tuned models, highlighting its efficiency and generalization across diverse tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
