Pinned Loading

1. SaGE SaGE Public

   Forked from vnnm404/SaGE

   The official repo implementing, SaGE: Evaluating Moral Consistency in Large Language Models.

   Python

2. QuittingAgents QuittingAgents Public

   Code for the paper: Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety

   Python

3. sycophancy-detection sycophancy-detection Public

   This project implements activation-based detection approaches from representation engineering to identify when LLMs give sycophantic (user-pleasing rather than truthful) responses.

   Python 1

4. picoVLM picoVLM Public

   Forked from huggingface/nanoVLM

   Editing nanovlm for efficiency

   Python

5. idecir-Towards-Effective-Paraphrasing-for-Information-Disguise idecir-Towards-Effective-Paraphrasing-for-Information-Disguise Public

   Forked from idecir/idecir-Towards-Effective-Paraphrasing-for-Information-Disguise

   Python