[ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`

Your efficient and accurate answer verification system for RL training.

[ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities

[AAAI25] Official Repo of Paper `ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates`

Generate diverse coding questions and verifiable solutions - all in one framework

[EMNLP 24] Official Implementation of CLEANGEN: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

Source Code for "EDC: Effective and Efficient Dialog Comprehension For Dialog State Tracking" (NAACL 2024)