SSR-GRPO：融合监督与语义标识符的电商密集检索强化学习
原标题：SSR-GRPO: Integrating Supervision and Semantic IDs into Reinforcement Learning for Dense Retrieval in E-commerce
AI 摘要
本文提出 SSR-GRPO，一种用于电商密集检索的强化学习框架，通过引入语义标识符（SIDs）和双视角相关性评估，解决 R-GRPO 中候选池噪声和奖励偏差问题。该方法利用 SIDs 挖掘难负样本，并集成掩码函数和 Retrieval-DPO 任务，提升模型细粒度语义区分能力。离线与在线实验验证了其有效性，并已部署于大规模电商平台。
正文节选
SSR-GRPO: Integrating Supervision and Semantic IDs into Reinforcement Learning for Dense Retrieval in E-commerceDOI: 10.1145/3799682.3840101Conference: Proceedings of the 35th ACM International Conference on Information and Knowledge Management; November 07–11, 2026; Rome, ItalyProceedings of the 35th ACM International Conference on Information and Knowledge Management (CIKM ’26), November 07–11, 2026, Rome, ItalyISBN: 979-8-4007-2539-5/2026/11CCS: Information systems Retrieval models and rankin