AdaRec: Adaptive Recommendation with LLMs via Narrative Profiling and Dual-Channel Reasoning

We propose AdaRec, a few-shot in-context learning framework that leverages Large Language Models (LLMs) 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 e-commerce datasets demonstrate that AdaRec outperforms both machine learning models and LLM-based baselines by up to 8% in few-shot settings. In zero-shot scenarios, it achieves up to a 19% improvement over expert-crafted profiling, showing effectiveness for long-tail personalization with minimal interaction data. Moreover, 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.