Skip to content
#

nucleus-sampling

Here are 7 public repositories matching this topic...

Language: All
Filter by language

The LLM Defense Framework enhances large language model security through post-processing defenses and statistical guarantees based on one-class SVM. It combines advanced sampling methods with adaptive policy updates and comprehensive evaluation metrics, providing researchers and practitioners with tools to build more secure AI systems.

  • Updated Feb 6, 2025
  • Python

Orchestrator-worker multi-agent pattern: one planner, three independent workers with identical prompts but different sampling configs (temperature/top_p). Isolates what sampling alone changes in model behavior — conservative vs balanced vs creative brainstorming.

  • Updated Aug 27, 2026
  • Python

Improve this page

Add a description, image, and links to the nucleus-sampling topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the nucleus-sampling topic, visit your repo's landing page and select "manage topics."

Learn more