发表机构
Kuaishou Technology（快手科技）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出SARA框架，将稀疏的用户可表述理由扩展为工业推荐系统的可扩展信号，通过数据引擎、MLLM对齐和排序集成，提升参与度并减少负面反馈。
AI 中文摘要
现代推荐系统主要从点击、观看时长和负面反馈等隐式行为中推断用户偏好，但这些信号揭示了用户的行为，而非他们喜欢或不喜欢内容的原因。本研究将用户可表述理由（AURs），即用户对其偏好的自然语言解释，作为一类新的极性感知和理由级文本信号用于推荐。尽管AURs具有潜在价值，但由于其天然稀疏、质量往往较低且仅覆盖一小部分物品，难以在工业系统中使用。我们提出了SARA（扩展可表述理由），一个将稀疏AURs转化为可扩展推荐信号的工业框架。SARA首先构建了一个数据引擎，从2.4亿快手直播用户中获取并策展AURs，生成SARA-HQ，一个质量受控且以作者为中心的理由数据集。然后，通过大规模SFT和质量精炼DPO，将通用MLLM对齐为SARA-7B，将理由生成从86,564名覆盖AUR的作者扩展到全1000万作者空间。最后，SARA-Ranker通过理由感知交互建模和拒绝记忆建模，将生成的正向和负向理由集成到生产排序中。广泛的离线评估、人工校准和在线A/B测试表明，SARA-7B生成的比强MLLM基线更具体、极性一致且有依据的理由，而SARA-Ranker在生产中提升了参与度并减少了负面反馈。SARA已部署并每日刷新超过30天，确立了可表述理由作为工业推荐系统实用的一等文本信号的地位。
英文摘要
We presented SARA, an industrial framework that transforms sparse articulated user rationales into scalable recommendation signals. Its data engine curates questionnaire responses into SARA-HQ, providing explicit preference supervision for aligning SARA-7B through SFT and Quality-Refining DPO. This alignment extends rationale generation from $86{,}564$ questionnaire-covered authors to the full $10$M-author space. SARA-Ranker translates the generated positive and negative rationales into features for user--author interaction modeling and negative-feedback history modeling, connecting articulated reasons to production ranking. Evaluation on unseen authors demonstrates that SARA-7B generates more specific, relevant, and grounded rationales than the evaluated general-purpose MLLMs. On top of a strong industrial ranking baseline with multimodal features, separate online A/B tests show that positive-rationale integration increases watch time by $0.99\%$, while negative-rationale integration reduces Hate feedback by $8.16\%$. Daily refresh and more than $30$ days of production deployment further demonstrate the operational feasibility of the approach. These findings establish articulated rationales as a useful complement to behavioral and content signals, and demonstrate a practical role for MLLMs in scaling sparse human explanations into preference information that improves industrial recommendation.
