TATK：基于知识验证的三重感知Top-K学习用于基于LLM的序列推荐
TATK: Triple-Aware Top-K Learning with Knowledge-Grounded Verification for LLM-based Sequential Recommendation
浏览论文内容
中文总结 AI 辅助
TATK通过结合Top-K学习与知识验证，解决基于LLM的序列推荐中全目录Top-K排序问题，在36个指标上全面超越基线。
中文摘要 AI 辅助
基于LLM的序列推荐器通常将下一项预测视为文本生成，但这种接口与全目录Top-K排序的匹配度较差。我们提出TATK，一个三重感知框架，将Top-K学习（TKL）与知识验证（KGV）相结合，用于基于LLM的序列推荐。Top-K学习将上下文感知的元数据知识图谱提示与位置感知的Top-K奖励相结合，使训练与排序效用对齐；知识验证则在单次LLM前向传播后，利用相同的元数据派生项目图，对Top-M候选进行结构感知重排序。我们在Amazon Reviews 2023的音乐乐器、CD和黑胶唱片、视频游戏数据集上，采用匹配的R2ec风格全目录协议评估TATK。实验使用Gemma-2-2B-It和Qwen2.5-3B-Instruct作为骨干模型，与序列、生成、知识图谱增强和推理增强基线进行比较，并包含组件、奖励形状、序列扰动、重排序、关系质量和候选池诊断。TATK在所有36个报告指标上优于匹配的R2ec复现。在NDCG@10上，它在三个数据集上分别将Qwen提升了8.05%、4.26%和3.78%，将Gemma提升了27.03%、10.52%和10.23%，同时推理延迟保持在Base RecPO的1.17倍以内。诊断表明，结构证据对于具有可靠知识图谱支持的可恢复Top-M候选最有用，当元数据关系稀疏或嘈杂时应进行门控。
英文摘要
LLM-based sequential recommenders usually cast next-item prediction as text generation, but this interface is poorly matched to full-catalog top-K ranking. We propose TATK, a Triple-Aware framework that couples Top-K Learning (TKL) with Knowledge-Grounded Verification (KGV) for LLM-based sequential recommendation. Top-K Learning combines context-aware metadata-KG prompt grounding with position-aware top-K rewards, aligning training with ranking utility; Knowledge-Grounded Verification then applies structure-aware reranking over the top-M candidates after a single LLM forward pass, using the same metadata-derived item graph. We evaluate TATK on Musical Instruments, CDs and Vinyl, and Video Games from Amazon Reviews 2023 under a matched R2ec-style full-catalog protocol. Experiments use Gemma-2-2B-It and Qwen2.5-3B-Instruct backbones, compare against sequential, generative, KG-augmented, and reasoning-enhanced baselines, and include component, reward-shape, sequence-perturbation, reranking, relation-quality, and candidate-pool diagnostics. TATK improves over the matched R2ec reproduction on all 36 reported metrics. On NDCG@10, it improves Qwen by 8.05%, 4.26%, and 3.78% on the three datasets, and improves Gemma by 27.03%, 10.52%, and 10.23%, while keeping inference within 1.17x of Base RecPO latency. The diagnostics show that structural evidence is most useful for recoverable top-M candidates with reliable KG support, and should be gated when metadata relations are sparse or noisy.
发表机构
- East China University of Science and Technology（华东理工大学）
- Hong Kong Institute of Science & Innovation（香港科创中心）
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
- Westlake University（西湖大学）
机构由 AI 辅助整理，请以论文原文为准。
