Tag
data quality
2 articles
Research/May 16
Why fine-tuning LLMs for domain tasks is the right default
Fine-tuning is the best default when an LLM must be accurate in a narrow domain.
Research/May 11
Microsoft’s GoalCover finds fine-tuning gaps
Microsoft Research’s GoalCover spots missing capabilities in fine-tuning data before training, and improved Qwen-3-14B reward scores.