🏢 Intel Labs
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
·269 words·2 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Large Language Models
🏢 Intel Labs
Boost fine-tuned LLMs’ performance without sacrificing safety by merging pre- and post-tuning model weights!