CELLO: Causal Evaluation of Large Vision-Language Models

TL;DR

This paper introduces CELLO, a comprehensive dataset and evaluation framework for assessing and improving the causal reasoning abilities of large vision-language models, highlighting current limitations and potential enhancements.

Contribution

The paper presents a new dataset, CELLO, with explicit causal graphs and a novel prompting strategy, CELLO-CoT, to evaluate and enhance causal reasoning in LVLMs.

Findings

LVLMs struggle with causal reasoning tasks.

CELLO-CoT improves model performance on causal questions.

Explicit causal graphs aid in understanding model reasoning.

Abstract

Causal reasoning is fundamental to human intelligence and crucial for effective decision-making in real-world environments. Despite recent advancements in large vision-language models (LVLMs), their ability to comprehend causality remains unclear. Previous work typically focuses on commonsense causality between events and/or actions, which is insufficient for applications like embodied agents and lacks the explicitly defined causal graphs required for formal causal reasoning. To overcome these limitations, we introduce a fine-grained and unified definition of causality involving interactions between humans and/or objects. Building on the definition, we construct a novel dataset, CELLO, consisting of 14,094 causal questions across all four levels of causality: discovery, association, intervention, and counterfactual. This dataset surpasses traditional commonsense causality by including explicit causal graphs that detail the interactions between humans and objects. Extensive experiments on CELLO reveal that current LVLMs still struggle with causal reasoning tasks, but they can benefit significantly from our proposed CELLO-CoT, a causally inspired chain-of-thought prompting strategy. Both quantitative and qualitative analyses from this study provide valuable insights for future research. Our project page is at https://github.com/OpenCausaLab/CELLO.