Further training a pre-trained LLM on a domain-specific dataset to improve performance on specialized tasks. Fine-tuning adjusts model weights to better match a target behavior or domain.
Fine-tuning takes a general-purpose LLM and specializes it by continuing training on curated examples. This improves accuracy and consistency compared to using the base model with prompts alone.
When NOT to fine-tune: your use case is general, you lack quality training data, or the task can be handled with good prompting. For most business applications, RAG and prompt engineering deliver 90% of the value at 10% of the cost of fine-tuning.
Anthropic's AI assistant with industry-leading reasoning and safety
Weekly AI tool reviews, news digests, and how-to guides.
Join 12,000+ builders