Fine-tuned small language models can reach high accuracy on function calling, but zero-shot and few-shot performance is poor, and the study's few-shot results are compromised by using test-set examples in the prompt.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling
Fine-tuned small language models can reach high accuracy on function calling, but zero-shot and few-shot performance is poor, and the study's few-shot results are compromised by using test-set examples in the prompt.