Evaluating an LLM (gemma-2b-it) for fairness, stereotype bias, and toxicity on DecodingTrust prompts, with a prompt-based debiasing experiment. Uppsala MSc (1RT730).
-
Updated
Jun 5, 2026 - Jupyter Notebook
#
decodingtrust
Here are 2 public repositories matching this topic...
A comprehensive evaluation of LLM trustworthiness (toxicity, bias, and privacy) using the DecodingTrust framework on Microsoft Phi-2.
-
Updated
Jan 10, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the decodingtrust topic, visit your repo's landing page and select "manage topics."