Pinned Loading

1. weak-to-strong-search weak-to-strong-search Public

   [NeurIPS'24] Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models

   Python 31 3

2. emulated-disalignment emulated-disalignment Public

   [ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

   Python 29

3. modpo modpo Public

   [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization

   Python 52 3

4. INTENT INTENT Public

   [UIST'22] INTENT: Interactive Tensor Transformation Synthesis

   Python 7 2