Home icon

Power Your LLM Training and Evaluation with the New SageMaker AI Generative AI Tools

Machine Learning Blog



AWS has introduced two new SageMaker AI Generative AI tools to help power Large Language Model (LLM) training and evaluation:

  • Text Ranking Template: Allows human annotators to rank AI-generated responses based on custom criteria like relevance, clarity, and accuracy
  • Question and Answer Template: Enables creation of high-quality Q&A pairs from text passages for model training
  • Both templates can be used in the SageMaker AI console or via API
  • Supports Reinforcement Learning from Human Feedback (RLHF) and Supervised Fine-Tuning (SFT)
  • Helps improve model outputs by aligning them more closely with human preferences

These tools provide a streamlined approach for generating datasets and evaluating generative AI models, making it easier for developers to create more accurate and reliable AI solutions.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Jul 17
2025
Evaluating generative AI models with Amazon Nova LLM-as-a-Judge on Amazon SageMaker AI
Apr 22
2025
Supercharge your LLM performance with Amazon SageMaker Large Model Inference container v15
Apr 24
2024
Improve LLM performance with human and AI feedback on Amazon SageMaker for Amazon Engineering
Feb 6
2026
Evaluate generative AI models with an Amazon Nova rubric-based LLM judge on Amazon SageMaker AI (Part 2)

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.