Zero-Shot Recommendation as Language Modeling

2021/12/08 by Damien Sileo, Sileo, Damien, Wout Vossen +3 · 7 citations
Computer Science · #Topic Modeling #Recommender Systems and Techniques #Multimodal Machine Learning Applications

paper · doi:10.48550/arxiv.2112.04184

Abstract

Recommendation is the task of ranking items (e.g. movies or products) according to individual user needs. Current systems rely on collaborative filtering and content-based techniques, which both require structured training data. We propose a framework for recommendation with off-the-shelf pretrained language models (LM) that only used unstructured text corpora as training data. If a user u liked Matrix and Inception, we construct a textual prompt, e.g. \textit"Movies like Matrix, Inception, " to estimate the affinity between u and m with LM likelihood. We motivate our idea with a corpus analysis, evaluate several prompt structures, and we compare LM-based recommendation with standard matrix factorization trained on different data regimes. The code for our experiments is publicly available (https://colab.research.google.com/drive/1f1mlZ-FGaLGdo5rPzxf3vemKllbh2esT?usp=sharing).

Cited by

• GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models
• Towards Efficient Hypergraph and Multi-LLM Agent Recommender Systems
• A Survey on Generative Recommendation: Data, Model, and Tasks
• Large-scale User Game Lifecycle Representation Learning
• Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation
• SocRipple: A Two-Stage Framework for Cold-Start Video Recommendations
• KERAG_R: Knowledge-Enhanced Retrieval-Augmented Generation for Recommendation

Related

• Zero-Shot Next-Item Recommendation using Large Pretrained Language Models
• Pre-train, Prompt and Recommendation: A Comprehensive Survey of Language Modelling Paradigm Adaptations in Recommender Systems
• Large Language Models as Narrative-Driven Recommenders
• Language-Based User Profiles for Recommendation
• A Language-Driven Framework for Improving Personalized Recommendations: Merging LLMs with Traditional Algorithms