让大模型生成可解释的推荐标识，提升推荐效果与透明度
PushDualGen: Enabling LLMs to Generate Semantic IDs with Interpretable Copy for Industrial Push Recommendation
- 先生成语义ID，再生成可跳过的解释副本，轻量高效
- 在线测试显示播放率提升8.50%，用户不满率下降37.70%
- 适合需要可解释性与大规模部署的工业推荐系统
快手推送推荐系统需向近十亿用户主动推送个性化内容以提升参与度。生成式推荐通过语义ID实现端到端个性化，但其黑箱特性使推荐逻辑难以追溯，阻碍实际部署。OneRec-Thinking虽引入思维链（CoT）提升可解释性，但显著增加推理成本。为支持大规模工业应用，我们提出PushDualGen，一种轻量级生成器：先生成语义ID（SID），再生成一个可跳过的复制解释。该模型已部署于快手推送推荐系统。在线A/B测试表明，推送视频的有效播放率相对提升8.50%，用户不满意率相对下降37.70%。长期来看，该方法优化了内容生态，提升了长尾视频曝光度。
原文摘要 · Abstract (English)
Push recommendation in KuaiShou proactively delivers personalized content to nearly one billion users to facilitate their engagement. Recently, generative recommendation has achieved end-to-end user personalization through semantic ID. However, their black- box characteristics make recommendation logics difficult to trace, hindering their deployment. OneRec-Thinking addresses this by incorporating CoT before generating SIDs, but this significantly increases inference cost. To support large-scale industrial applications, we propose PushDualGen, a lightweight generator, which first generates the SID and then produces a copy as a skippable explanation. PushDualGen has been deployed in Kuaishou's push recommendation system. Online A/B tests demonstrate the effectiveness of PushDualGen, delivering significant improvements in both user attraction and satisfaction. The effective play rate for videos recommended to users has relatively increased by 8.50%, while the dissatisfaction rate has relatively fallen by 37.70%. In the long term, PushDualGen optimises the content ecosystem, providing more exposure for long-tail videos.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。