Zero-Shot Recommendation as Language Modeling

8 Dec 2021  ·  Damien Sileo, Wout Vossen, Robbe Raymaekers ·

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 \textit{Matrix} and \textit{Inception}, we construct a textual prompt, e.g. \textit{"Movies like Matrix, Inception, ${<}m{>}$"} 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 (

PDF Abstract


Introduced in the Paper:


Used in the Paper:

MovieLens WebText
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Language Modelling language-modeling-recommendation GPT2 1:1 Accuracy 48.8 # 1


No methods listed for this paper. Add relevant methods here