A Comprehensive Evaluation on Event Reasoning of Large Language Models

TL;DR

This paper introduces EV2, a comprehensive benchmark for evaluating large language models' event reasoning abilities across various relations and paradigms, revealing their strengths and limitations.

Contribution

It presents a new benchmark EV2 for systematic evaluation of event reasoning in LLMs and offers insights into their capabilities and gaps.

Findings

LLMs can perform event reasoning but with unsatisfactory accuracy.

There is an imbalance in LLMs' event reasoning abilities.

Aligning LLMs' use of event schema knowledge improves reasoning performance.

Abstract

Event reasoning is a fundamental ability that underlies many applications. It requires event schema knowledge to perform global reasoning and needs to deal with the diversity of the inter-event relations and the reasoning paradigms. How well LLMs accomplish event reasoning on various relations and reasoning paradigms remains unknown. To mitigate this disparity, we comprehensively evaluate the abilities of event reasoning of LLMs. We introduce a novel benchmark EV2 for EValuation of EVent reasoning. EV2 consists of two levels of evaluation of schema and instance and is comprehensive in relations and reasoning paradigms. We conduct extensive experiments on EV2. We find that LLMs have abilities to accomplish event reasoning but their performances are far from satisfactory. We also notice the imbalance of event reasoning abilities in LLMs. Besides, LLMs have event schema knowledge, however, they're not aligned with humans on how to utilize the knowledge. Based on these findings, we guide the LLMs in utilizing the event schema knowledge as memory leading to improvements on event reasoning.