让大模型在历史数据少时也能准确推理时间知识图谱
RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion
- 用规则检索多跳历史结构，弥补数据稀疏问题
- 对比学习微调轻量适配器，提升关系语义编码能力
- 测试时基于相似性迭代过滤生成，提升预测合理性
时间知识图谱（TKG）将动态事实表示为带时间戳的实体间关系。完成任务需模型对随时间演化的结构进行推理。尽管大语言模型（LLM）在此任务中展现出潜力，但现有方法常过度依赖监督微调，在历史证据稀疏或缺失时表现不佳。我们提出RECIPE-TKG，一种轻量且数据高效的方法，旨在提升稀疏历史条件下的准确率与泛化能力。该框架结合：(1) 基于规则的多跳检索以获取结构多样化的历史信息；(2) 对轻量适配器进行对比微调，编码关系语义；(3) 测试时语义过滤，基于嵌入相似性迭代优化生成结果。在四个TKG基准上的实验表明，相较于以往基于LLM的方法，RECIPE-TKG在Hits@10上实现最高达30.6%的相对提升。此外，即使在历史信息有限的情况下，其生成结果也更具语义一致性。
原文摘要 · Abstract (English)
Temporal Knowledge Graphs (TKGs) represent dynamic facts as timestamped relations between entities. TKG completion involves forecasting missing or future links, requiring models to reason over time-evolving structure. While LLMs show promise for this task, existing approaches often overemphasize supervised fine-tuning and struggle particularly when historical evidence is limited or missing. We introduce RECIPE-TKG, a lightweight and data-efficient framework designed to improve accuracy and generalization in settings with sparse historical context. It combines (1) rule-based multi-hop retrieval for structurally diverse history, (2) contrastive fine-tuning of lightweight adapters to encode relational semantics, and (3) test-time semantic filtering to iteratively refine generations based on embedding similarity. Experiments on four TKG benchmarks show that RECIPE-TKG outperforms previous LLM-based approaches, achieving up to 30.6\% relative improvement in Hits@10. Moreover, our proposed framework produces more semantically coherent predictions, even for the samples with limited historical context.
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。