Skip to content

Dataset · AdaptLLM

Finance tasks for LLM evaluation

AdaptLLM/finance-tasks

Evaluation sets for LLM domain adaptation in finance from the ICLR 2024 paper.

What's inside

These are evaluation datasets from the paper Adapting Large Language Models via Reading Comprehension (ICLR 2024). They belong to the financial domain and are designed to test LLMs after continued pre-training. The card specifies text-classification, question-answering, and zero-shot-classification tasks; data is in English.

What you can do with it

  • Evaluating financial QA models
  • Testing zero-shot classification in finance
  • Comparing LLM domain adaptation methods
Tasks
Text classification, Question answering, Zero shot classification
Languages
English
Size
10K–100K rows
Downloads this month
1.5K
Likes
85

How to load it

from datasets import load_dataset

ds = load_dataset("AdaptLLM/finance-tasks")