#fine-tuning
5 papers
-
inspiration
Fine-Tuning Is Usually Not the First Move
Reaching for fine-tuning to fix a model is often the expensive wrong turn. Most problems that look like they need fine-tuning are really retrieval or prompting problems. Fine-tuning changes behavior and style; it is a poor and costly way to inject knowledge.
-
whitepaper
Synthetic Data for Fine-Tuning: The Engineering Guide
Training on AI-generated data is now the default path for open-model fine-tuning. The pattern works — but it has failure modes that are not visible in benchmark scores. This paper maps five practical methods (Self-Instruct, Evol-Instruct, Orca, phi, SPIN), the model collapse risk that applies to all of them, and the design checklist that keeps a synthetic data pipeline from degrading.
-
inspiration
Merging Is Not Training
Model merging combines two or more fine-tuned LLMs into a single model without any gradient updates. No data. No compute budget. No training run. The result inherits capabilities from every source model — if you pick the right algorithm.
-
inspiration
LoRA Is Not Fine-Tuning
LoRA does not update your model. It adds a thin, low-rank correction on top — and that distinction changes how you think about deployment, switching, and scale.
-
whitepaper
Fine-Tuning, RAG, or Prompting: An Engineering Decision
Three techniques can improve LLM output quality: prompt engineering, retrieval-augmented generation, and fine-tuning. Each solves a different problem. Choosing the wrong one wastes months and produces worse results than the right one done simply.