Zero-Shot Next-Item Recommendation using Large Pretrained Language Models
#chatgpt #recommendations #llms
This video discusses how we can use LLMs like ChatGPT/GPT-4 and others to build a zero-shot next-item recommender system. We particularly discuss how to build movie recommendation system using Large Language models (LLMs)
Abstract: Large language models (LLMs) have achieved impressive zero-shot performance in various natural language processing (NLP) tasks, demonstrating their capabilities for inference without training examples. Despite their success, no research has yet explored the potential of LLMs to perform next-item recommendations in the zero-shot setting. We have identified two major challenges that must be addressed to enable LLMs to act effectively as recommenders. First, the recommendation space can be extremely large for LLMs, and LLMs do not know about the target user's past interacted items and preferences. To address this gap, we propose a prompting strategy called Zero-Shot Next-Item Recommendation (NIR) prompting that directs LLMs to make next-item recommendations. Specifically, the NIR-based strategy involves using an external module to generate candidate items based on user-filtering or item-filtering. Our strategy incorporates a 3-step prompting that guides GPT-3 to carry subtasks that capture the user's preferences, select representative previously watched movies, and recommend a ranked list of 10 movies. We evaluate the proposed approach using GPT-3 on MovieLens 100K dataset and show that it achieves strong zero-shot performance, even outperforming some strong sequential recommendation models trained on the entire training dataset. These promising results highlight the ample research opportunities to use LLMs as recommenders.
⏩ Paper Title: Zero-Shot Next-Item Recommendation using Large Pretrained Language Models
⏩ Paper: https://arxiv.org/abs/2304.03153
⏩ Author: Lei Wang, Ee-Peng Lim
⏩ Organisation: Singapore Management University
⏩ IMPORTANT LINKS
Code Link: https://github.com/AGI-Edgerunners/LL...
BART paper summary: • BART: Denoising Sequence-to-Sequence Pre-t...
T5 paper summary: • T5: Exploring Limits of Transfer Learning ...
Pegasus paper summary: • PEGASUS: Pre-training with Gap-Sentences f...
Research Paper Summaries: • Simple Unsupervised Keyphrase Extraction u...
Enjoy reading articles? then consider subscribing to Medium membership, it is just 5$ a month for unlimited access to all free/paid content.
Subscribe now - / membership
*********************************************
⏩ Youtube - / @techvizthedatascienceguy
⏩ LinkedIn - / prakhar21
⏩ Medium - / prakhar.mishra
⏩ GitHub - https://github.com/prakhar21
*********************************************
⏩ Please feel free to share out the content and subscribe to my channel - / @techvizthedatascienceguy
Tools I use for making videos :)
⏩ iPad - https://tinyurl.com/y39p6pwc
⏩ Apple Pencil - https://tinyurl.com/y5rk8txn
⏩ GoodNotes - https://tinyurl.com/y627cfsa
#techviz #datascienceguy #deeplearning #ai #transformers #recommendersystems #machinelearning
About Me:
I am Prakhar Mishra and this channel is my passion project. I am currently pursuing my MS (by research) in Data Science. I have an industry work-ex of 4+ years in the field of Data Science and Machine Learning with a particular focus on Natural Language Processing (NLP).