LLMRS: Unlocking Potentials of LLM-Based Recommender Systems for Software Purchase
This work addresses the challenge of generating reliable recommendations for software purchases, but it is incremental as it applies existing LLM methods to a specific domain.
The paper tackled the problem of capturing user preferences in recommendation systems by proposing LLMRS, an LLM-based zero-shot recommender system that encodes user reviews into scores for software purchase recommendations. The results show that LLMRS outperforms a ranking-based baseline model on the Amazon product reviews dataset.
Recommendation systems are ubiquitous, from Spotify playlist suggestions to Amazon product suggestions. Nevertheless, depending on the methodology or the dataset, these systems typically fail to capture user preferences and generate general recommendations. Recent advancements in Large Language Models (LLM) offer promising results for analyzing user queries. However, employing these models to capture user preferences and efficiency remains an open question. In this paper, we propose LLMRS, an LLM-based zero-shot recommender system where we employ pre-trained LLM to encode user reviews into a review score and generate user-tailored recommendations. We experimented with LLMRS on a real-world dataset, the Amazon product reviews, for software purchase use cases. The results show that LLMRS outperforms the ranking-based baseline model while successfully capturing meaningful information from product reviews, thereby providing more reliable recommendations.