STAR: A Simple Training-free Approach for Recommendations using Large Language Models
Preprint
Abstract
Recent progress in large language models (LLMs) offers promising new approaches for recommendation system (RecSys) tasks. While the current state-of-the-art methods rely on fine-tuning LLMs to achieve optimal results, this process is costly and introduces significant engineering complexities. Conversely, methods that bypass fine-tuning and use LLMs directly are less resource-intensive but often fail to fully capture both semantic and collaborative information, resulting in sub-optimal performance compared to their fine-tuned counterparts. In this paper, we propose a Simple Training-free Approach for Recommendation (STAR), a framework that utilizes LLMs and can be applied to various recommendation tasks without the need for fine-tuning. Our approach involves a retrieval stage that uses semantic embeddings from LLMs combined with collaborative user information to retrieve candidate items. We then apply an LLM for pairwise ranking to enhance next-item prediction. Experimental results on the Amazon Review dataset show competitive performance for next item prediction, even with our retrieval stage alone. Our full method achieves Hits@10 performance of +23.8% on Beauty, +37.5% on Toys and Games, and -1.8% on Sports and Outdoors relative to the best supervised models. This framework offers an effective alternative to traditional supervised models, highlighting the potential of LLMs in recommendation systems without extensive training or custom architectures.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Large Language Models for Information Retrieval: A SurveyACM Transactions on Information Systems, 2025
- Recommendation as Instruction Following: A Large Language Model Empowered Recommendation ApproachACM Transactions on Information Systems, 2025
- How Can Recommender Systems Benefit from Large Language Models: A SurveyACM Transactions on Information Systems, 2025
- Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations2024
- Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System2024
- When large language models meet personalization: perspectives of challenges and opportunitiesWorld Wide Web, 2024
- Recommender Systems in the Era of Large Language Models (LLMs)IEEE Transactions on Knowledge and Data Engineering, 2024
- Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels2024
- Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents2023
- Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models2022