EvEval: A Comprehensive Evaluation of Event Semantics for Large Language Models

TL;DR

This paper introduces EVEVAL, a comprehensive benchmark with multiple datasets to evaluate large language models' capabilities in understanding, reasoning, and predicting event semantics, addressing a key gap in NLP evaluation.

Contribution

It proposes a new evaluation framework and benchmark, EVEVAL, for systematically assessing LLMs' event semantic processing abilities across various aspects.

Findings

LLMs show varying performance across different event semantic tasks.

EVEVAL reveals specific strengths and weaknesses of current models.

The benchmark facilitates targeted improvements in event semantic understanding.

Abstract

Events serve as fundamental units of occurrence within various contexts. The processing of event semantics in textual information forms the basis of numerous natural language processing (NLP) applications. Recent studies have begun leveraging large language models (LLMs) to address event semantic processing. However, the extent that LLMs can effectively tackle these challenges remains uncertain. Furthermore, the lack of a comprehensive evaluation framework for event semantic processing poses a significant challenge in evaluating these capabilities. In this paper, we propose an overarching framework for event semantic processing, encompassing understanding, reasoning, and prediction, along with their fine-grained aspects. To comprehensively evaluate the event semantic processing abilities of models, we introduce a novel benchmark called EVEVAL. We collect 8 datasets that cover all aspects of event semantic processing. Extensive experiments are conducted on EVEVAL, leading to several noteworthy findings based on the obtained results.