MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset

TL;DR

This paper introduces MARS, a comprehensive benchmark dataset designed to evaluate large language models' abilities to reason about situational changes and transitions, addressing a critical gap in metaphysical reasoning evaluation.

Contribution

It proposes a novel three-step reasoning framework for distributional changes and provides the first benchmark dataset, MARS, to systematically assess LLMs' metaphysical reasoning abilities.

Findings

All tested LLMs struggle with the tasks, even after fine-tuning.

Pre-training on conceptual taxonomies can improve reasoning performance.

The benchmark reveals significant challenges in metaphysical reasoning for current models.

Abstract

To enable Large Language Models (LLMs) to function as conscious agents with generalizable reasoning capabilities, it is crucial that they possess the reasoning ability to comprehend situational changes (transitions) in distribution triggered by environmental factors or actions from other agents. Despite its fundamental significance, this ability remains underexplored due to the complexity of modeling infinite possible changes in an event and their associated distributions, coupled with the lack of benchmark data with situational transitions. Addressing these gaps, we propose a novel formulation of reasoning with distributional changes as a three-step discriminative process, termed as MetAphysical ReaSoning. We then introduce the first-ever benchmark, MARS, comprising three tasks corresponding to each step. These tasks systematically assess LLMs' capabilities in reasoning the plausibility of (i) changes in actions, (ii) states caused by changed actions, and (iii) situational transitions driven by changes in action. Extensive evaluations with 20 (L)LMs of varying sizes and methods indicate that all three tasks in this process pose significant challenges, even for state-of-the-art LLMs and LMs after fine-tuning. Further analyses reveal potential causes for the underperformance of LLMs and demonstrate that pre-training them on large-scale conceptualization taxonomies can potentially enhance their metaphysical reasoning capabilities. Our data and models are publicly accessible at https://github.com/HKUST-KnowComp/MARS.