RecLM: Recommendation Instruction Tuning
RecLM integrates large language models with collaborative filtering via instruction tuning and a reinforcement learning reward to enhance recommendation performance, especially for sparse and zero-shot settings.
Published Dec 26, 2024Code ★ 111arXiv ↗
Only vote on papers you've read. Sign in with GitHub to vote.
RecLM delivers a model-agnostic RL-augmented instruction-tuning framework that strengthens sparse-data recommendations via plug-and-play GNN integration, though whether its reward genuinely reshapes preference diversity or merely smooths sparse IDs remains unresolved without ablation and latency clarity.
Abstract
Modern recommender systems aim to deeply understand users' complex preferences through their past interactions. While deep collaborative filtering approaches using Graph Neural Networks (GNNs) excel at capturing user-item relationships, their effectiveness is limited when handling sparse data or zero-shot scenarios, primarily due to constraints in ID-based embedding functions. To address these challenges, we propose a model-agnostic recommendation instruction-tuning paradigm that seamlessly integrates large language models with collaborative filtering. Our proposed $\underline{Rec}$ommendation $\underline{L}$anguage $\underline{M}$odel (RecLM) enhances the capture of user preference diversity through a carefully designed reinforcement learning reward function that facilitates self-augmentation of language models. Comprehensive evaluations demonstrate significant advantages of our approach across various settings, and its plug-and-play compatibility with state-of-the-art recommender systems results in notable performance enhancements. The implementation of our RecLM framework is publicly available at: https://github.com/HKUDS/RecLM.