Task selection
Choosing the right task type for your model is the crucial first step in the distil labs workflow. Currently, our platform provides specialized support for two fundamental task types: classification and open book question answering.
Classification
Classification models analyze input text and assign it to one category from a fixed set of options. This task type is particularly effective when you need deterministic categorization rather than open-ended generation.
Example Use Cases
Some common application areas for classification include:
- Intent detection for customer service queries
- Content moderation (toxic/safe, spam/not spam)
- Sentiment analysis (positive/negative/neutral)
- Topic categorization for knowledge bases
- Triaging support tickets by department
Open Book Question Answering
Open book question answering involves generating responses to questions based on provided context. Open book QA focuses on information extraction and comprehension of the provided information.
Open book QA is particularly valuable when you need to leverage specific information sources rather than general knowledge. It’s the right choice when your application needs to:
- Build Retrieval Augmented Generation (RAG) architectures where it’s impractical for the model to memorize the entire knowledge base.
- Extract precise information from documents or reference materials.
Example Use Cases
Example use cases where open book QA excels include:
- Customer support systems that answer based on product documentation
- Legal document analysis and question answering
- Technical documentation assistants
- Knowledge base or FAQ automation
- Research assistants that answer based on specific papers or texts
Choosing Between Classification and Open Book QA
Deciding between these task types often comes down to the nature of your desired output. Classification is about selecting the right category, while open book QA is about generating contextually relevant answers.