ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.11034
17
0

CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models

21 May 2025
Aneesh Komanduri
Karuna Bhaila
Xintao Wu
    ReLMLRMELM
ArXiv (abs)PDFHTML
Main:8 Pages
10 Figures
Bibliography:3 Pages
11 Tables
Appendix:8 Pages
Abstract

Large language models (LLMs) have shown remarkable ability in various language tasks, especially with their emergent in-context learning capability. Extending LLMs to incorporate visual inputs, large vision-language models (LVLMs) have shown impressive performance in tasks such as recognition and visual question answering (VQA). Despite increasing interest in the utility of LLMs in causal reasoning tasks such as causal discovery and counterfactual reasoning, there has been relatively little work showcasing the abilities of LVLMs on visual causal reasoning tasks. We take this opportunity to formally introduce a comprehensive causal reasoning benchmark for multi-modal in-context learning from LVLMs. Our CausalVLBench encompasses three representative tasks: causal structure inference, intervention target prediction, and counterfactual prediction. We evaluate the ability of state-of-the-art open-source LVLMs on our causal reasoning tasks across three causal representation learning datasets and demonstrate their fundamental strengths and weaknesses. We hope that our benchmark elucidates the drawbacks of existing vision-language models and motivates new directions and paradigms in improving the visual causal reasoning abilities of LVLMs.

View on arXiv
@article{komanduri2025_2506.11034,
  title={ CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models },
  author={ Aneesh Komanduri and Karuna Bhaila and Xintao Wu },
  journal={arXiv preprint arXiv:2506.11034},
  year={ 2025 }
}
Comments on this paper