 |
To address the limitations of simple prompts, the "Self-Consistency" technique was applied . This approach involves querying the LMM three times for each image and employing a voting process to select the most consistent description . As indicated by the t-SNE visualization in Figure 3.7, this method successfully separates real and AI-generated descriptions within the feature space . While producing high-quality data, the requirement for multiple queries and voting rounds significantly increases computational cost and latency . |
IEEE/ICACT20260070 Slide.10
[Big Slide]