Distilling Event Sequence Knowledge From Large Language Models
Abstract
Event sequence models have been found to be highly effective in the analysis and prediction of events. Building such models requires availability of abundant high-quality event sequence data. In certain applications, however, clean structured event sequences are not available, and automated sequence extraction results in data that is too noisy and incomplete. In this paper, we explore the use of Large Language Models (LLMs) to generate event sequences that can effectively be used for event model construction. This can be viewed as a mechanism of distilling event sequence knowledge from LLMs. Our approach relies on a Knowledge Graph (KG) of event concepts with partial causal relations to guide the generative LLMs for causal event sequence generation. We show that our approach can generate high-quality event sequences, filling a knowledge gap in the input KG. Furthermore, we show that the generated sequences can be used to mine interesting patterns and construct high-quality models for event prediction. We release our sequence generation code and evaluation framework, as well as corpus of event sequence data.