用大模型理解事件语义，高效建模时间点过程。
TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Models
- 直接用事件文本描述，融合语义与时间信息
- 参数高效微调，准确率优于现有方法
- 适合需要理解事件含义的时序预测场景
时间点过程（TPPs）广泛用于建模社交网络、交通系统和电商等领域中事件发生的时间与顺序。本文提出TPP-LLM框架，将大语言模型（LLMs）与TPPs结合，同时捕捉事件序列的语义与时间特性。不同于传统方法依赖类别化的事件类型表示，TPP-LLM直接使用事件类型的文本描述，从而获取文本中蕴含的丰富语义信息。虽然大模型擅长理解事件语义，但在建模时间模式方面表现较弱。为此，TPP-LLM引入时间嵌入，并采用参数高效微调（PEFT）方法，在无需大量重训练的前提下有效学习时间动态，显著提升预测准确率与计算效率。在多个真实世界数据集上的实验表明，TPP-LLM在序列建模与事件预测任务中均优于当前最优基线，验证了将大模型与时间点过程结合的有效性。
原文摘要 · Abstract (English)
Temporal point processes (TPPs) are widely used to model the timing and occurrence of events in domains such as social networks, transportation systems, and e-commerce. In this paper, we introduce TPP-LLM, a novel framework that integrates large language models (LLMs) with TPPs to capture both the semantic and temporal aspects of event sequences. Unlike traditional methods that rely on categorical event type representations, TPP-LLM directly utilizes the textual descriptions of event types, enabling the model to capture rich semantic information embedded in the text. While LLMs excel at understanding event semantics, they are less adept at capturing temporal patterns. To address this, TPP-LLM incorporates temporal embeddings and employs parameter-efficient fine-tuning (PEFT) methods to effectively learn temporal dynamics without extensive retraining. This approach improves both predictive accuracy and computational efficiency. Experimental results across diverse real-world datasets demonstrate that TPP-LLM outperforms state-of-the-art baselines in sequence modeling and event prediction, highlighting the benefits of combining LLMs with TPPs.
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。