The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation
This work addresses the challenge of making LLMs more effective as sequential recommenders, offering an incremental improvement in demonstration aggregation for in-context learning.
The paper tackles the problem of improving sequential recommendation using large language models (LLMs) by proposing LLMSRec-Syn, a method that aggregates multiple user demonstrations into one to enhance in-context learning, which outperforms state-of-the-art LLM-based methods and sometimes matches or exceeds supervised learning approaches on three datasets.
Large language models (LLMs) have shown excellent performance on various NLP tasks. To use LLMs as strong sequential recommenders, we explore the in-context learning approach to sequential recommendation. We investigate the effects of instruction format, task consistency, demonstration selection, and number of demonstrations. As increasing the number of demonstrations in ICL does not improve accuracy despite using a long prompt, we propose a novel method called LLMSRec-Syn that incorporates multiple demonstration users into one aggregated demonstration. Our experiments on three recommendation datasets show that LLMSRec-Syn outperforms state-of-the-art LLM-based sequential recommendation methods. In some cases, LLMSRec-Syn can perform on par with or even better than supervised learning methods. Our code is publicly available at https://github.com/demoleiwang/LLMSRec_Syn.