2025
InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
AAAI 2025technical
Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a fine-tuned open-source model to generate additional data to…