> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bespokelabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# SimpleStrat

> Use the StratifiedGenerator block to get more varied answers to the same question.

If you ask an LLM the same open question many times, e.g., "Name a periodic element", it tends to give the same few answers. The `StratifiedGenerator` block makes the answers more varied. It is based on the SimpleStrat method from the paper [Stratified Generation for Artificial Data in Question Answering](https://arxiv.org/abs/2410.09038).

## Example

```python theme={null}
from datasets import Dataset

from bespokelabs.curator.blocks.simplestrat import StratifiedGenerator

# Ask the same question 20 times. The numbers keep the rows distinct.
questions = Dataset.from_dict({"question": [f"{i}. Name a periodic element" for i in range(20)]})

generator = StratifiedGenerator(model_name="gpt-4o-mini")
qa_pairs = generator(questions).dataset

print(f"Generated {len(qa_pairs)} QA pairs")
print(qa_pairs[0])
```

The input dataset needs a `question` column. The output dataset has a `question` column and an `answer` column.

## How it works

`StratifiedGenerator` runs four `curator.LLM` steps in a row.

1. For each question, the LLM lists true or false properties that an answer may have, e.g., "The element is a metal."
2. For each property, the LLM estimates how likely it is that a random answer has it.
3. The LLM removes properties that overlap and keeps at most three, preferring ones close to a 50% chance.
4. For each question, Curator picks one property at random, weighted by its probability, and adds it to the question. The LLM then answers the new question.

Because each question gets a different property, the answers cover more of the possible range.

## Settings

`StratifiedGenerator` passes its arguments to each of the four steps, so it takes the same arguments as `curator.LLM`.

```python theme={null}
generator = StratifiedGenerator(
    model_name="gpt-4o",
    generation_params={"temperature": 0.7},
)
```

## Save the results

The result is a Hugging Face `Dataset`, so you can push it to the Hub.

```python theme={null}
qa_pairs.push_to_hub("<hf-org>/<dataset-name>")
```

## Troubleshooting

If the answers are still too similar, raise `temperature` in `generation_params`.

If you get API errors, try another model or change the rate limits in `backend_params`. See the [API reference](/curator/api-reference#backend-parameters).