Text classification: a fine-tuned Hugging Face encoder vs a local LLM, measured
DistilBERT fine-tuned in minutes vs zero-shot and few-shot Qwen3 on the same 300 news stories. Real accuracy, macro F1, latency and cost per million items.
Articles / tag
2 articles.
DistilBERT fine-tuned in minutes vs zero-shot and few-shot Qwen3 on the same 300 news stories. Real accuracy, macro F1, latency and cost per million items.
Paraphrases, label-conditioned generation and hard negatives from a local LLM, four quality filters, and a real experiment on whether the synthetic text helped.