Popular repositories Loading

1. Eraser Eraser Public

   Source code for the paper "Eraser: Jailbreaking defense in large language models via unlearning harmful knowledge".

   Python 9 2

2. PrivacyRestore PrivacyRestore Public

   Official Code of ACL2025 "PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration"

   Python 9 1

3. RCP-Merging RCP-Merging Public

   [AAAI2026]: Official Code of "RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior"

   Python 8 1

4. SEA SEA Public

   [ACL'25 Main Track] Repository for " SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings"

   Python 7

5. ConsistentEE ConsistentEE Public

   [AAAI 2024 Main Track] Repository for the paper titled "ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference"

   Python 6 1

6. GenderAlign GenderAlign Public

   GenderAlign is a dataset consisting of 8,362 single-turn dialogues designed to mitigate a wide range of gender biases in language models.

   6 1