Dataset Viewer
Auto-converted to Parquet Duplicate
The dataset viewer is not available for this split.
Couldn't cast array of type list<element: int64> to int64
Error code:   UnexpectedError

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

Financial Exam MCQ Training Dataset

A bilingual training dataset of financial and accounting multiple-choice questions in English and Chinese, formatted for instruction tuning and answer selection tasks.

Dataset Structure

  • Format: Multiple-choice questions
  • Language: English and Chinese
  • Domain: Accounting, finance, auditing, taxation, and financial regulations
  • Size: 596 examples
  • Files:
    • train-00000-of-00001-en.parquet
    • train-00000-of-00001-cn.parquet
    • train-00000-of-00002-en.parquet
    • train-00000-of-00002-cn.parquet

Fields

  • id: Unique identifier (e.g. zh_0001, en_0001)
  • query: Full MCQ prompt with instructions
  • answer: Correct answer letter (e.g. "b")
  • text: Question text without instructions
  • choices: List of answer labels (e.g. ["a", "b", "c", "d"])
  • gold: Zero-based index of the correct answer
  • conversations: Conversation turns with content and role
  • source_sheet: Source language sheet (Chinese or English)
  • original_correct_answer: Original answer label before normalization
  • reason: Explanation for the correct answer

Example

{
  "id": "zh_0001",
  "query": "请阅读下面的金融考试选择题,仅返回正确选项字母。\n\nQuestion: 下列关于内部控制的说法,正确的是哪一项?\n\nOptions:\na. 选项A\nb. 选项B\nc. 选项C\nd. 选项D\n\nAnswer:",
  "answer": "b",
  "text": "下列关于内部控制的说法,正确的是哪一项?",
  "choices": ["a", "b", "c", "d"],
  "gold": 1,
  "conversations": [
    {
      "content": "请阅读下面的金融考试选择题,仅返回正确选项字母。\n\nQuestion: 下列关于内部控制的说法,正确的是哪一项?\n\nOptions:\na. 选项A\nb. 选项B\nc. 选项C\nd. 选项D\n\nAnswer:",
      "role": "user"
    },
    {
      "content": "b",
      "role": "assistant"
    }
  ],
  "source_sheet": "Chinese",
  "original_correct_answer": "B",
  "reason": "正确答案为 B,因为该选项符合题目所述的控制原则。"
}

Usage

from datasets import load_dataset

dataset = load_dataset("YourUsername/your-dataset-name")
train_data = dataset['train']

for example in train_data:
    print(f"Question: {example['text']}")
    print(f"Choices: {example['choices']}")
    print(f"Answer: {example['answer']}")
    print(f"Reason: {example['reason']}")
Downloads last month
144