Language Models as Recommender Systems: Evaluations and Limitations
Language Models as Recommender Systems: Evaluations and Limitations
Yuhui Zhang,Hao Ding,4 著者,Hao Wang
2021
114 件の引用
TLDR
This work proposes to leverage pre-trained language models such as BERT and GPT as recommender systems and use prompts to reformulate the session-based recommendation task to a multi-token cloze task and observes strong linguistic bias when using PLMs as recommenders.