AdaRec: Adaptive Recommendation with LLMs via Narrative Profiling and Dual-Channel Reasoning
This addresses the problem of personalized recommendation with minimal data for e-commerce users, representing a novel method rather than an incremental improvement.
The authors tackled the problem of adaptive personalized recommendation by proposing AdaRec, a few-shot in-context learning framework that uses large language models with narrative profiling and dual-channel reasoning, achieving up to 8% improvement over baselines in few-shot settings and 19% in zero-shot scenarios.
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.