HiTZ/ifeval_gl

---
language:
- gl
pretty_name: IFEval GL
task_categories:
- text-generation
tags:
- ifeval
- instruction-following
- galician
- evaluation
size_categories:
- n<1K
---

# IFEval GL

## Dataset Summary

IFEval GL is a Galician instruction-following evaluation dataset in JSONL format.
It contains prompts together with the corresponding instruction identifiers and argument constraints used for evaluation.

## Dataset Structure

| Split | Rows | Features |
|-------|-----:|---------:|
| train | 541 | 4 |

## Features

| Feature | Type | Description |
|---|---|---|
| `key` | integer | Unique example identifier |
| `prompt` | string | Instruction prompt in Galician |
| `instruction_id_list` | list[string] | List of instruction categories associated with the example |
| `kwargs` | list[dict] | Parameters associated with each instruction |

## Example

```json
{"key":1000,"prompt":"Fai un resumo de máis de 300 palabras sobre a páxina de Wikipedia \"https://en.wikipedia.org/wiki/Raymond_III,_Count_of_Tripoli\". Non uses ningunha coma e destaca polo menos 3 seccións que teñan títulos en formato markdown, por exemplo *sección destacada parte 1*, *sección destacada parte 2*, *sección destacada parte 3*.","instruction_id_list":["punctuation:no_comma","detectable_format:number_highlighted_sections","length_constraints:number_words"],"kwargs":[{},{"num_highlights":3},{"relation":"at least","num_words":300}]}