通过轻量级可审计测试，揭示推荐系统性能提升的真实来源。
Auditing Semantic Gains in Sequential Recommendation: A Lightweight Recovery Test
- 设计三专家融合模型，分离评估语义、协同与共现信号贡献。
- 在亚马逊美妆等数据集上超越基线7%-12%，验证语义信息有效性。
- 证明性能提升依赖真实物品文本对应关系，非模型复杂度或推理能力。
近期基于语义和生成检索的推荐系统相比仅使用ID的序列基线有显著提升，但其增益来自语言模型推理、语义ID生成、端到端语义架构、更强的离线物品表示，还是语义与协同信号互补仍不明确。本文通过LIME-Rec——一种轻量且可审计的恢复测试，探究这一归因模糊性。LIME-Rec结合三个独立专家：SASRec序列专家、ItemCF共现专家，以及基于冻结BAAI/bge-base-en-v1.5物品嵌入的语义专家。三者全库得分按用户归一化后，通过可审计的分值级融合与有界历史校准结合。融合门控与校准头仅在验证集上训练，无需服务时的语言模型推理，且保持各专家贡献可独立检视。在Amazon Beauty、Toys和Sports数据集上，LIME-Rec的R@10分别为0.0996、0.1105和0.0593，优于最强对比基线7.0%-12.0%。无历史校准的三专家融合始终优于校准后的SASRec，表明校准本身无法解释性能恢复。随机打乱物品文本嵌入后，R@10下降13.6%-17.5%，说明增益依赖于真实的物品-文本对应关系，而非额外表示容量。结果表明，在将改进归因于实时语言建模、语义ID生成或更重语义架构前，应先排除来自离线物品表示的轻量恢复与透明融合的可能性。
原文摘要 · Abstract (English)
Recent semantic and generative-retrieval recommenders report substantial improvements over ID-only sequential baselines, but it remains unclear whether these gains arise from language-model reasoning, semantic-ID generation, end-to-end semantic architectures, stronger offline item representations, or complementary semantic and collaborative signals. We investigate this attribution ambiguity through LIME-Rec, a lightweight and auditable recovery test. LIME-Rec combines three independent experts: a SASRec sequential expert, an ItemCF co-occurrence expert, and a semantic expert based on frozen BAAI/bge-base-en-v1.5 item embeddings. Their full-catalog scores are normalized per user and combined through auditable score-level fusion followed by bounded history calibration. The fusion gate and calibration head are fitted on validation data only, require no serving-time language-model inference, and keep each expert contribution separately inspectable. On Amazon Beauty, Toys, and Sports, LIME-Rec achieves R@10 scores of 0.0996, 0.1105, and 0.0593, outperforming the strongest comparison baseline by 7.0%-12.0%. Three-expert fusion without history calibration consistently outperforms calibrated SASRec, showing that calibration alone does not explain the recovery. Randomly permuting item-text embeddings across item IDs reduces R@10 by 13.6%-17.5%, indicating that the gains depend on genuine item-text correspondence rather than additional representation capacity. These results suggest that lightweight recovery from offline item representations and transparent fusion should be ruled out before improvements are attributed to serving-time language modeling, semantic-ID generation, or heavier semantic machinery.
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。