Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs
Anzeige
Ähnliche Artikel
The Register – Headlines
•
Sony rolls out a standard way to measure bias in how AI describes what it 'sees'
arXiv – cs.AI
•
Detecting Prefix Bias in LLM-based Reward Models
arXiv – cs.LG
•
ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning
arXiv – cs.LG
•
On the Societal Impact of Machine Learning
arXiv – cs.AI
•
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
arXiv – cs.AI
•
RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration