Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities

Sachit Menon, Richard Zemel, Carl Vondrick


Abstract
When presented with questions involving visual thinking, humans naturally switch reasoning modalities, often forming mental images or drawing visual aids. Large language models have shown promising results in arithmetic and symbolic reasoning by expressing intermediate reasoning in text as a chain of thought, yet struggle to extend this capability to answer text queries that are easily solved by visual reasoning, even with extensive multimodal pretraining. We introduce a simple method, whiteboard-of-thought prompting, to unlock the visual reasoning capabilities of multimodal large language models across modalities. Whiteboard-of-thought prompting provides multimodal large language models with a metaphorical ‘whiteboard’ to draw out reasoning steps as images, then returns these images back to the model for further processing. We find this can be accomplished with no demonstrations or specialized modules, instead leveraging models’ existing ability to write code with libraries such as Matplotlib and Turtle. This simple approach shows state-of-the-art results on four difficult natural language tasks that involve visual and spatial reasoning. We identify multiple settings where GPT-4o using chain-of-thought fails dramatically, including more than one where it achieves 0% accuracy, while whiteboard-of-thought enables up to 92% accuracy in these same settings. We present a detailed exploration of where the technique succeeds as well as its sources of error.
Anthology ID:
2024.emnlp-main.1117
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
20016–20031
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1117
DOI:
10.18653/v1/2024.emnlp-main.1117
Bibkey:
Cite (ACL):
Sachit Menon, Richard Zemel, and Carl Vondrick. 2024. Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 20016–20031, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities (Menon et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1117.pdf