Adding lightweight multi-token auxiliary heads with a weighted future-token loss improves supervised fine-tuning of Llama-3-8B-Instruct across five diverse tasks.
Code Alpaca: An Instruction-following LLaMA model for code generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Large Language Models with Concept-Aware Fine-Tuning
Adding lightweight multi-token auxiliary heads with a weighted future-token loss improves supervised fine-tuning of Llama-3-8B-Instruct across five diverse tasks.