Gen AI and LLM - Set 2

123456789101112131415
Across
  1. 3. An input given to a model to generate a response or output.
  2. 4. The primary output of language models, consisting of written words.
  3. 6. A conversational interaction, often facilitated by AI.
  4. 9. Adjusting a pre-trained model on a smaller dataset for specific tasks.
  5. 10. A type of neural network architecture that underpins many modern LLMs.
  6. 11. A unit of text processed by language models, typically a word or subword.
  7. 13. A modeling error where a model learns noise in the training data instead of the underlying pattern.
  8. 15. The surrounding information that helps models understand the meaning of text.
Down
  1. 1. A learning approach where a model performs tasks without specific training examples for those tasks.
  2. 2. Information used to train AI models, including text and images.
  3. 5. The process of teaching a model using large datasets to improve its performance.
  4. 7. Referring to models that can create new content, such as text or images.
  5. 8. A numerical representation of words or phrases in vector space for better processing by models.
  6. 12. The act of generating predictions or outputs from a trained model.
  7. 14. A mechanism in neural networks that allows models to focus on relevant parts of the input data when generating output.