Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
Paper
•
2503.00555
•
Published
Georgia Institute of Technology
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
gatech's activity
TianshengHuang
authored
a
paper
8 days ago
clcatalan
authored
a
paper
15 days ago
TianshengHuang
authored
a
paper
about 2 months ago
judyhoffman
authored
a
paper
3 months ago
TianshengHuang
authored
6
papers
4 months ago
PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models
Paper
•
2402.01118
•
Published
•
31
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
Paper
•
2409.18169
•
Published
Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
Paper
•
2402.01109
•
Published
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack
Paper
•
2405.18641
•
Published
Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning
Paper
•
2408.09600
•
Published
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
Paper
•
2409.01586
•
Published
Dhruv2012
updated
a
dataset
5 months ago
judyhoffman
authored
a
paper
over 1 year ago
judyhoffman
authored
a
paper
almost 2 years ago