Empowering Few-Shot Recommender Systems With Large Language Models-Enhanced Representations
Recommender systems utilizing explicit feedback have witnessed significant advancements and widespread applications over the past years. However, generating recommendations in few-shot scenarios remains a persistent challenge. Recently, large language models (LLMs) have emerged as a promising soluti...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10440582/ |
| _version_ | 1797289808257613824 |
|---|---|
| author | Zhoumeng Wang |
| author_facet | Zhoumeng Wang |
| author_sort | Zhoumeng Wang |
| collection | DOAJ |
| description | Recommender systems utilizing explicit feedback have witnessed significant advancements and widespread applications over the past years. However, generating recommendations in few-shot scenarios remains a persistent challenge. Recently, large language models (LLMs) have emerged as a promising solution for addressing natural language processing (NLP) tasks, thereby offering novel insights into tackling the few-shot scenarios encountered by explicit feedback-based recommender systems. To bridge recommender systems and LLMs, we devise a prompting template that generates user and item representations based on explicit feedback. Subsequently, we integrate these LLM-processed representations into various recommendation models to evaluate their significance across diverse recommendation tasks. Our ablation experiments and case study analysis collectively demonstrate the effectiveness of LLMs in processing explicit feedback, highlighting that LLMs equipped with generative and logical reasoning capabilities can effectively serve as a component of recommender systems to enhance their performance in few-shot scenarios. Furthermore, the broad adaptability of LLMs augments the generalization potential of recommender models, despite certain inherent constraints. We anticipate that our study can inspire researchers to delve deeper into the multifaceted dimensions of LLMs’ involvement in recommender systems and contribute to the advancement of the explicit feedback-based recommender systems field. |
| first_indexed | 2024-03-07T19:11:22Z |
| format | Article |
| id | doaj.art-7a27d6d1e30b4eeeaf7281503d30869c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-07T19:11:22Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7a27d6d1e30b4eeeaf7281503d30869c2024-03-01T00:00:54ZengIEEEIEEE Access2169-35362024-01-0112291442915310.1109/ACCESS.2024.336802710440582Empowering Few-Shot Recommender Systems With Large Language Models-Enhanced RepresentationsZhoumeng Wang0https://orcid.org/0009-0000-3547-3172Marketing Programme, The Chinese University of Hong Kong Business School, Hong Kong, ChinaRecommender systems utilizing explicit feedback have witnessed significant advancements and widespread applications over the past years. However, generating recommendations in few-shot scenarios remains a persistent challenge. Recently, large language models (LLMs) have emerged as a promising solution for addressing natural language processing (NLP) tasks, thereby offering novel insights into tackling the few-shot scenarios encountered by explicit feedback-based recommender systems. To bridge recommender systems and LLMs, we devise a prompting template that generates user and item representations based on explicit feedback. Subsequently, we integrate these LLM-processed representations into various recommendation models to evaluate their significance across diverse recommendation tasks. Our ablation experiments and case study analysis collectively demonstrate the effectiveness of LLMs in processing explicit feedback, highlighting that LLMs equipped with generative and logical reasoning capabilities can effectively serve as a component of recommender systems to enhance their performance in few-shot scenarios. Furthermore, the broad adaptability of LLMs augments the generalization potential of recommender models, despite certain inherent constraints. We anticipate that our study can inspire researchers to delve deeper into the multifaceted dimensions of LLMs’ involvement in recommender systems and contribute to the advancement of the explicit feedback-based recommender systems field.https://ieeexplore.ieee.org/document/10440582/Large language modelsrecommender systemsChatGPTrepresentations |
| spellingShingle | Zhoumeng Wang Empowering Few-Shot Recommender Systems With Large Language Models-Enhanced Representations IEEE Access Large language models recommender systems ChatGPT representations |
| title | Empowering Few-Shot Recommender Systems With Large Language Models-Enhanced Representations |
| title_full | Empowering Few-Shot Recommender Systems With Large Language Models-Enhanced Representations |
| title_fullStr | Empowering Few-Shot Recommender Systems With Large Language Models-Enhanced Representations |
| title_full_unstemmed | Empowering Few-Shot Recommender Systems With Large Language Models-Enhanced Representations |
| title_short | Empowering Few-Shot Recommender Systems With Large Language Models-Enhanced Representations |
| title_sort | empowering few shot recommender systems with large language models enhanced representations |
| topic | Large language models recommender systems ChatGPT representations |
| url | https://ieeexplore.ieee.org/document/10440582/ |
| work_keys_str_mv | AT zhoumengwang empoweringfewshotrecommendersystemswithlargelanguagemodelsenhancedrepresentations |