SARM: 基于大语言模型的语义锚点用于端到端实时直播排序
SARM: LLM-Augmented Semantic Anchor for End-to-End Live-Streaming Ranking
AI总结：
SARM通过整合自然语言语义锚点到端到端排序优化中，提升实时直播内容排序的精度和效率。
摘要：
大规模实时直播推荐需要在严格实时服务约束下对非平稳内容语义进行精确建模。在工业部署中，两种常见方法存在根本性限制：离散语义抽象通过聚类牺牲了描述精度，而密集多模态嵌入是独立提取的，仍然与排序优化弱相关，限制了细粒度内容感知排序。为解决这些限制，我们提出了SARM，一种端到端排序架构，将自然语言语义锚点直接整合到排序优化中，使模型能够根据多模态内容生成细粒度作者表示。每个语义锚点被表示为可学习的文本令牌，与排序特征联合优化，使模型能够适应内容描述到排序目标。轻量级双令牌门控设计捕捉领域特定的实时直播语义，而非对称部署策略保持了低延迟的在线训练和服务。广泛的离线评估和大规模A/B测试显示了对生产基线的一致改进。SARM已完全部署，并每天为超过4亿用户服务。
英文摘要：
Large-scale live-streaming recommendation requires precise modeling of non-stationary content semantics under strict real-time serving constraints. In industrial deployment, two common approaches exhibit fundamental limitations: discrete semantic abstractions sacrifice descriptive precision through clustering, while dense multimodal embeddings are extracted independently and remain weakly aligned with ranking optimization, limiting fine-grained content-aware ranking. To address these limitations, we propose \textbf{SARM}, an end-to-end ranking architecture that integrates natural-language semantic anchors directly into ranking optimization, enabling fine-grained author representations conditioned on multimodal content. Each semantic anchor is represented as learnable text tokens jointly optimized with ranking features, allowing the model to adapt content descriptions to ranking objectives. A lightweight dual-token gated design captures domain-specific live-streaming semantics, while an asymmetric deployment strategy preserves low-latency online training and serving. Extensive offline evaluation and large-scale A/B tests show consistent improvements over production baselines. SARM is fully deployed and serves over 400 million users daily.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
