Skip to content
#

refusal

Here are 47 public repositories matching this topic...

Early warning for LLM safety drift during fine-tuning: a Circuit Integrity Score read from the model's refusal circuit flags unsafe checkpoints before harm is measurable, with SafeTune repair and AuditKIT audit.

  • Updated Nov 16, 2026
  • Jupyter Notebook

Every RAG eval reports faithfulness. None reports over-refusal beside it. An eval harness and policy engine for refusal correctness in regulated RAG: synthetic KYC/AML corpus, deterministic verifier, and a refusal policy you can commit, hash and audit.

  • Updated Sep 1, 2026
  • Python

An experiment in mechanistic interpretability exploring how refusal behaviour is represented inside language models. Using Qwen2.5-1.5B-Instruct, I reproduce the single-direction refusal intervention described by Arditi et al. (2024), investigate where the refusal signal emerges across layers, and test what happens when it is removed.

  • Updated Oct 31, 2026
  • Python

Add this topic to your repo

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

Learn more