Chua Shei Pern

vincchua's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 6 hours ago

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs

Paper • 2509.05367 • Published Jan 10 • 1

liked a model about 7 hours ago

microsoft/HARC

Text Generation • Updated about 10 hours ago • 3

upvoted a paper about 10 hours ago

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment

Paper • 2607.00572 • Published 1 day ago • 2

published 3 models about 10 hours ago

microsoft/HARC-Qwen2.5-7B-Instruct

Text Generation • 8B • Updated about 10 hours ago

microsoft/HARC-Llama-3.1-8B-Instruct

Text Generation • 8B • Updated about 10 hours ago

microsoft/HARC

Text Generation • Updated about 10 hours ago • 3

upvoted a collection about 10 hours ago

HARC

Collection

A family of safety-aligned instruction models trained with HARC • 4 items • Updated about 10 hours ago • 1

updated a collection about 10 hours ago

HARC

Collection

A family of safety-aligned instruction models trained with HARC • 4 items • Updated about 10 hours ago • 1

updated 2 models about 10 hours ago

microsoft/HARC-Qwen2.5-7B-Instruct

Text Generation • 8B • Updated about 10 hours ago

microsoft/HARC-Llama-3.1-8B-Instruct

Text Generation • 8B • Updated about 10 hours ago

updated a model about 12 hours ago

microsoft/HARC

Text Generation • Updated about 10 hours ago • 3

authored a paper 2 months ago

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs

Paper • 2509.05367 • Published Jan 10 • 1