Large Language Models are Competitive Near Cold-start Recommenders for Language- and Item-based Preferences
Top Cited Papers
Open Access
- 14 September 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 890-896
Abstract
Traditional recommender systems leverage users’ item preference history to recommend novel content that users may like. However, modern dialog interfaces that allow users to express language-based preferences offer a fundamentally different modality for preference input. Inspired by recent successes of prompting paradigms for large language models (LLMs), we study their use for making recommendations from both item-based and language-based preferences in comparison to state-of-the-art item-based collaborative filtering (CF) methods. To support this investigation, we collect a new dataset consisting of both item-based and language-based preferences elicited from users along with their ratings on a variety of (biased) recommended items and (unbiased) random items. Among numerous experimental results, we find that LLMs provide competitive recommendation performance for pure language-based preferences (no item preferences) in the near cold-start case in comparison to item-based CF methods, despite having no supervised training for this specific task (zero-shot) or only a few labels (few-shot). This is particularly promising as language-based preference representations are more explainable and scrutable than item-based or vector-based representations.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Defining and Supporting Narrative-driven Recommendation2017
- Understanding How People Use Natural Language to Ask for Recommendations2017
- Neural Collaborative Filtering2017
- Diversity, Serendipity, Novelty, and CoverageACM Transactions on Interactive Intelligent Systems, 2016
- Towards Conversational Recommender Systems2016
- Interview process learning for top-n recommendation2013
- SLIM: Sparse Linear Methods for Top-N Recommender Systems2011
- MyMediaLite2011
- Item-based collaborative filtering recommendation algorithms2001
- Good intentions, bad habits, and effects of forming implementation intentions on healthy eatingEuropean Journal of Social Psychology, 1999