Learn Before
Multimodal Chain-of-Thought Reasoning
Multimodal chain-of-thought reasoning extends step-by-step logical prompting to inputs that combine both text and images. Language models utilizing these multimodal inputs achieve higher reasoning accuracy compared to when they rely on text input alone.
0
1
Tags
D2L
Dive into Deep Learning @ D2L
Related
Example of a Model Initiating Chain-of-Thought Reasoning
A user is trying to solve a word problem using a large language model. They use two different prompts and receive two different responses.
Prompt 1: "A farmer has 5 pens, and each pen holds 8 chickens. The farmer buys 10 more chickens. How many chickens does the farmer have in total?" Response 1: "The farmer has 50 chickens in total."
Prompt 2: "A farmer has 5 pens, and each pen holds 8 chickens. The farmer buys 10 more chickens. How many chickens does the farmer have in total? Let
Modifying a Prompt for Step-by-Step Reasoning
Improving AI Reasoning for a Multi-Step Problem
Improving Chain-of-Thought Reasoning
Zero-Shot Chain-of-Thought Reasoning
Multimodal Chain-of-Thought Reasoning