IRAIMar 20, 2024

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

arXiv:2403.13574v212 citationsh-index: 25
Originality Incremental advance
AI Analysis

This addresses the need for more comprehensive user preference modeling in online video platforms by incorporating comment interactions, though it appears incremental as it builds on existing sequential recommendation methods.

The paper tackles the problem of joint video and comment recommendation by proposing LSVCR, which integrates user interactions with both videos and comments using a sequential recommendation model supplemented by a large language model, achieving a 4.13% gain in comment watch time in online A/B testing.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes