Fine-tuning the teacher before knowledge distillation improves the distilled model most reliably when teacher and student share a vocabulary, and fine-tuning both gives the best scores overall.
Using large language models to understand telecom standards,
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
-
Knowledge Distillation of Domain-adapted LLMs for Question-Answering in Telecom
Fine-tuning the teacher before knowledge distillation improves the distilled model most reliably when teacher and student share a vocabulary, and fine-tuning both gives the best scores overall.