NER: general vs fine-tuned, and when to switch
Start with a general NER model to learn what you need. Fine-tune a small model once your entities are specific to your domain, and handle negation and context separately.
Short, opinionated notes from our own projects and demos. Every topic has our verdict, the evidence behind it, and a way to try it.
Each topic carries one of four stances, like the rings on a technology radar.
When to fine-tune a small model instead of prompting a large one, how to measure the difference, and what we have shipped.
2 topicsRetrieval-augmented generation in practice: chunking, overlap, retrieval and reranking, and how to tell whether any of it helped.
1 topicUsing large and small language models where they earn their place: cost, privacy, running them locally, and where they fall short.
1 topic4 topics
Start with a general NER model to learn what you need. Fine-tune a small model once your entities are specific to your domain, and handle negation and context separately.
Reranking is worth trying when your retrieval is close but not reliable. It is not free accuracy, and the only way to know is to measure it on your own questions.
A small local language model is a good fit for narrow, text-in text-out jobs where the answer is already in the input. It is a poor source of knowledge, and it needs a person checking its output.
For a high-volume, privacy-sensitive coding workflow, a pipeline of small, task-specific models beat repeated LLM calls on cost, speed, privacy and recall. We would not assume that holds for every task.
No topics found.
Want this kind of thinking applied to your data? Tell us the problem and we will tell you what we would do.
View AllSend us the paragraph you'd normally write to a colleague. We'll get back to you within 24 hours.
hello@tathastha.com