Pinned Loading

1. Trustworthy-ML-Lab/Steer2Edit Trustworthy-ML-Lab/Steer2Edit Public

   Python 1

2. Trustworthy-ML-Lab/ThinkEdit Trustworthy-ML-Lab/ThinkEdit Public

   [EMNLP 25] An effective and interpretable weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study uncovering how reasoning length is encoded in the model’s repr…

   Python 19 1

3. ADV-LLM ADV-LLM Public

   [NAACL 25] A framework to build powerful adversarial LLMs that can generate jailbreak prompts.

   Python 8

4. Trustworthy-ML-Lab/CB-LLMs Trustworthy-ML-Lab/CB-LLMs Public

   [ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliability, transparency, and trustworthiness.

   Python 33 19

5. Trustworthy-ML-Lab/when2tool Trustworthy-ML-Lab/when2tool Public

   Python 6 1

6. Trustworthy-ML-Lab/Agent-Cold-Start-Safety-Gap Trustworthy-ML-Lab/Agent-Cold-Start-Safety-Gap Public

   Python 1