SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
Paper • 2502.12025 • Published • 3
MidTool
community
AI & ML interests
None defined yet.
fqjiang
authored 4
papers over 1 year ago
Small Models Struggle to Learn from Strong Reasoners
Paper • 2502.12143 • Published • 40
CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
Paper • 2406.12257 • Published
Stronger Models are NOT Stronger Teachers for Instruction Tuning
Paper • 2411.07133 • Published • 39
fqjiang
authored 5
papers about 2 years ago
ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates
Paper • 2406.12935 • Published • 2
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
Paper • 2402.08983 • Published • 5
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
Paper • 2402.11753 • Published • 6
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
Paper • 2401.12242 • Published • 1
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Paper • 2406.08464 • Published • 72