Skip to content
#

ssit

Here is 1 public repository matching this topic...

SSIT: a label-free, gold-free test for whether LLM-judge position x verbosity bias corrections actually compose. No human labels, no model of the judge. Code, 7-judge/6-family pilot data, and pre-registered protocol for the NeurIPS 2026 JUDGe workshop paper.

  • Updated Sep 16, 2026
  • Python

Add this topic to your repo

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

Learn more