LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains

TL;DR

LLMAR is a tuning-free recommendation framework that leverages LLM reasoning to handle data sparsity and textual richness in industrial B2B applications, improving accuracy and reducing operational costs.

Contribution

It introduces a novel inference-driven annotation method, a self-correcting reflection loop, and a cost-effective architecture for industrial recommendation tasks.

Findings

Outperforms state-of-the-art models like SASRecF by up to 54.6% nDCG@10 on industrial data.

Achieves high inference efficiency at approximately $1 per 1,000 users.

Effectively captures user motives without training or fine-tuning.

Abstract

Industrial B2B applications (e.g., construction site risk prediction, material procurement) face extreme data sparsity yet feature rich textual interactions. In such environments, traditional ID-based collaborative filtering fails lacking co-occurrence signals, while fine-tuning standard Large Language Models (LLMs) incurs high operational costs and struggles with frequent data drift. We propose LLMAR (LLM-Annotated Recommendation), a tuning-free framework. Moving beyond simple embeddings, LLMAR systematically integrates LLM reasoning to capture user "latent motives" without any training process. We introduce three core contributions: (1) Inference-Driven Annotation: uses LLMs to transform behavioral history into structured semantic motives, enabling reasoning-based matching unattainable by ID-based methods; (2) Reflection Loop: a self-correction mechanism that refines generated queries to mitigate hallucinations and resolve "context competition" between past history and current instructions; and (3) Cost-Effective Architecture: relies on tuning-free components and asynchronous batch processing to minimize maintenance costs. Evaluations on public benchmarks (MovieLens-1M, Amazon Prime Pantry) and a sparse industrial dataset (construction risk prediction) demonstrate that LLMAR outperforms state-of-the-art learning-based models (SASRecF), achieving up to a 54.6% nDCG@10 improvement on the industrial dataset. Inference costs remain highly practical (~$1 per 1,000 users). For B2B domains where strict real-time latency is not critical, combining LLM reasoning with self-verification offers a superior alternative to training-based approaches across accuracy, explainability, and operational cost.