Enhancing Sequential Recommender with Large Language Models for Joint Video and Comment Recommendation

TL;DR

This paper introduces LSVCR, a novel recommendation system that combines sequential models and large language models to improve personalized video and comment recommendations by leveraging heterogeneous user interaction data.

Contribution

It proposes a two-stage training paradigm to effectively integrate sequential recommendation models with large language models for joint video and comment recommendation.

Findings

Achieves a 4.13% increase in comment watch time in online A/B tests.

Demonstrates improved recommendation accuracy in both video and comment tasks.

Effectively captures user preferences from heterogeneous interaction data.

Abstract

Nowadays, reading or writing comments on captivating videos has emerged as a critical part of the viewing experience on online video platforms. However, existing recommender systems primarily focus on users' interaction behaviors with videos, neglecting comment content and interaction in user preference modeling. In this paper, we propose a novel recommendation approach called LSVCR that utilizes user interaction histories with both videos and comments to jointly perform personalized video and comment recommendation. Specifically, our approach comprises two key components: sequential recommendation (SR) model and supplemental large language model (LLM) recommender. The SR model functions as the primary recommendation backbone (retained in deployment) of our method for efficient user preference modeling. Concurrently, we employ a LLM as the supplemental recommender (discarded in deployment) to better capture underlying user preferences derived from heterogeneous interaction behaviors. In order to integrate the strengths of the SR model and the supplemental LLM recommender, we introduce a two-stage training paradigm. The first stage, personalized preference alignment, aims to align the preference representations from both components, thereby enhancing the semantics of the SR model. The second stage, recommendation-oriented fine-tuning, involves fine-tuning the alignment-enhanced SR model according to specific objectives. Extensive experiments in both video and comment recommendation tasks demonstrate the effectiveness of LSVCR. Moreover, online A/B testing on KuaiShou platform verifies the practical benefits of our approach. In particular, we attain a cumulative gain of 4.13% in comment watch time.