Fine-tuning a 1B LLaMA model on a synthetic emotional-safety benchmark matches or beats 70B few-shot performance and a BERT baseline on three high-data categories, using under 2GB VRAM.
Llm-based edge intelligence: A comprehensive survey on architectures, applications, security and trustwor- thiness,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scaling behavior of large language models in emotional safety classification across sizes and tasks
Fine-tuning a 1B LLaMA model on a synthetic emotional-safety benchmark matches or beats 70B few-shot performance and a BERT baseline on three high-data categories, using under 2GB VRAM.