Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Xiaoming Shi, Siqiao Xue, Kangrui Wang, Fan Zhou, James Y. Zhang, JUN ZHOU, Chenhao Tan, Hongyuan Mei

Keywords: event sequences, irregular time series, event prediction, large language model, reasoning, few-shot prompting

TL;DR: We develop LAMP, a framework that utilizes the reasoning ability of large language models to help improve the prediction accuracy of event sequence models.

Abstract: Large language models have shown astonishing performance on a wide range of reasoning tasks. In this paper, we investigate whether they could reason about real-world events and help improve the prediction performance of event sequence models. We design LAMP, a framework that integrates a large language model in event prediction. Particularly, the language model performs abductive reasoning to assist an event sequence model: the event model proposes predictions on future events given the past; instructed by a few expert-annotated demonstrations, the language model learns to suggest possible causes for each proposal; a search module finds out the previous events that match the causes; a scoring function learns to examine whether the retrieved events could actually cause the proposal. Through extensive experiments on several challenging real-world datasets, we demonstrate that our framework---thanks to the reasoning capabilities of large language models---could significantly outperform the state-of-the-art event sequence models.

Submission Number: 2631