SFT data vs preference data: what each one needs
Supervised fine-tuning teaches a model what to say; preference data teaches it what is better. What goes into each dataset, how big it should be and who should write it.
2 min read
Supervised fine-tuning teaches a model what to say; preference data teaches it what is better. What goes into each dataset, how big it should be and who should write it.
2 min read
A step-by-step method for writing agent tasks with start states, success checks and rubrics, plus the mistakes that make agent benchmarks meaningless.
2 min read
The JSONL chat format used to fine-tune chatbots, what makes a good customer service dataset, and how many conversations you really need.
2 min read
Translated, scraped, generated or teacher-written: where Vietnamese math reasoning data comes from, how contamination skews scores, and what a good record looks like.
1 min read
Related: Conversational AI datasets · SFT dataset creation · AI agent task data