The paper introduces LLMRS, a recommender system based on Large Language Models (LLM), aimed at improving software purchase suggestions. Traditional recommender systems, while prevalent, often fail to accurately capture user preferences. LLMRS utilizes pre-trained LLM to translate user reviews into a review score, thus generating more personalized recommendations. The system was tested on a real-world dataset of Amazon product reviews for software purchases. The results demonstrated that LLMRS surpassed the ranking-based baseline model, effectively extracting valuable information from product reviews and providing more reliable recommendations.
Publication date: 15 Jan 2024
Project Page: Not provided
Paper: https://arxiv.org/pdf/2401.06676
