Skip to content
@Libr-AI

LibrAI

README.md

LibrAI

LibrAI uses artificial intelligence (AI) for AI governance, providing enterprise users with multidimensional, automated, and integrated AI safety services. Compared to current risk control solutions that heavily rely on human intervention, LibrAI proposed AI risk control solution can achieve 100 times the efficiency at 1/10th of the cost, ensuring a smooth implementation of AI.

Pinned Loading

  1. do-not-answer do-not-answer Public

    Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

    Jupyter Notebook 199 25

  2. OpenFactVerification OpenFactVerification Public

    Loki: Open-source solution designed to automate the process of verifying factuality

    Python 1k 45

  3. OpenRedTeaming OpenRedTeaming Public

    Papers about red teaming LLMs and Multimodal models.

    89 4

  4. fairlib fairlib Public

    A framework for assessing and improving classification fairness.

    Jupyter Notebook 33 8

Repositories

Showing 5 of 5 repositories
  • OpenRedTeaming Public

    Papers about red teaming LLMs and Multimodal models.

    Libr-AI/OpenRedTeaming’s past year of commit activity
    89 MIT 4 0 0 Updated Nov 22, 2024
  • OpenFactVerification Public

    Loki: Open-source solution designed to automate the process of verifying factuality

    Libr-AI/OpenFactVerification’s past year of commit activity
    Python 1,032 MIT 45 1 0 Updated Oct 3, 2024
  • do-not-answer Public

    Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

    Libr-AI/do-not-answer’s past year of commit activity
    Jupyter Notebook 199 Apache-2.0 25 0 0 Updated Jun 7, 2024
  • .github Public
    Libr-AI/.github’s past year of commit activity
    0 0 0 0 Updated Nov 11, 2023
  • fairlib Public

    A framework for assessing and improving classification fairness.

    Libr-AI/fairlib’s past year of commit activity
    Jupyter Notebook 33 Apache-2.0 8 1 2 Updated Jun 12, 2023

Top languages

Loading…

Most used topics

Loading…