Kuiz berkaitan panduan · Sederhana Tahap
Bias dan Stereotaip dalam Kuiz Penjana Imej AI
Menguji dari mana bias penjana imej berasal, cara penyelidik mengukurnya dengan gesaan neutral dan sebab pembetulan seperti penulisan semula segera boleh terlalu membetulkannya.
soalan 1 daripada 8
Mengapakah gesaan yang tidak menyebut jantina atau etnik masih menghasilkan imej yang berat sebelah?
Pratonton setiap soalan8 soalan
Jawapan dan penjelasan muncul semasa anda mengambil kuiz.
- Mengapakah gesaan yang tidak menyebut jantina atau etnik masih menghasilkan imej yang berat sebelah?
- The model randomly assigns attributes with equal probability
- The model falls back on the most typical picture it learned for the word, which reflects skewed data
- Users secretly add hidden terms
- Image generators cannot draw people accurately
- Apakah jenis data yang dipelajari oleh model seperti Stable Diffusion?
- Hand-drawn images commissioned for training
- Government census photographs
- Large collections of image-caption pairs scraped from the web
- Only stock photos with verified demographics
- Apakah kaedah yang biasa digunakan penyelidik untuk mengukur berat sebelah dalam penjana imej?
- Asking the model to rate its own fairness
- Counting how many words are in each prompt
- Checking image file sizes
- Generating many images for neutral prompts and comparing who appears
- Mengapakah projek Stable Bias menggunakan pengelompokan dan bukannya terus melabelkan kaum?
- Labeling someone's race from an image is itself unreliable and fraught
- Clustering is required by law
- Race labels made the images too large
- The images contained no people
- Apakah yang ditemui oleh analisis Bloomberg 2023 bagi imej Stable Diffusion?
- Outputs were perfectly balanced across all jobs
- Only landscapes showed bias
- High-paying jobs skewed toward lighter-skinned men
- The model refused to draw people at work
- What happened with Google's Gemini image generation in February 2024?
- It was paused after producing historically inaccurate diverse depictions
- It was praised for perfect historical accuracy
- It was banned in all countries
- It stopped generating landscapes
- What is the main weakness of simple behind-the-scenes prompt rewriting as a fix?
- It is too expensive to run
- It can be context-blind and alter prompts that specify a period or identity
- It makes images black and white
- It deletes the training data
- Which statement about the source of bias is accurate according to the guide?
- Bias comes only from training data
- Bias comes only from users' prompts
- Bias is fully solved by larger models
- Data, filtering, captioning, model design and post-training choices all shape bias