BRAINTEASER - Commonsense-Defying QA
Lateral thinking and commonsense-defying question answering task requiring annotators to select answers to brain teasers that defy default commonsense assumptions and provide explanations. Based on SemEval-2024 Task 9 (BRAINTEASER).
Configuration Fileconfig.yaml
This Potato config reproduces the annotation task. Save it as config.yaml and run potato start config.yaml to try it.
# BRAINTEASER - Commonsense-Defying QA
# Based on Jiang et al., SemEval 2024
# Paper: https://aclanthology.org/2024.semeval-1.274/
# Dataset: https://brainteasersem.github.io/
#
# This task asks annotators to solve brain teasers that defy default
# commonsense assumptions. Annotators select the best answer from four
# options and provide an explanation of their reasoning.
annotation_task_name: "BRAINTEASER - Commonsense-Defying QA"
task_dir: "."
data_files:
- sample-data.json
item_properties:
id_key: "id"
text_key: "text"
output_annotation_dir: "annotation_output/"
output_annotation_format: "json"
port: 8000
server_name: localhost
annotation_schemes:
- annotation_type: radio
name: answer_choice
description: "Select the best answer to the brain teaser."
labels:
- "A"
- "B"
- "C"
- "D"
keyboard_shortcuts:
"A": "1"
"B": "2"
"C": "3"
"D": "4"
tooltips:
"A": "Option A"
"B": "Option B"
"C": "Option C"
"D": "Option D"
- annotation_type: text
name: explanation
description: "Explain your reasoning for the selected answer."
annotation_instructions: |
You will be shown a brain teaser question with four answer options. The task
covers two subtasks: Sentence Puzzles (reasoning defies commonsense at the
sentence level) and Word Puzzles (the answer violates the default meaning of
a word and hinges on its letter composition). Your task is to:
1. Read the question carefully. These are lateral thinking puzzles that may
defy your initial commonsense assumptions.
2. Consider all four options before selecting your answer. Following the
BRAINTEASER format, the fourth option may be "None of the above."
3. Think creatively -- the answer may involve wordplay, unconventional logic,
or challenging default assumptions.
4. Provide a brief explanation of your reasoning.
html_layout: |
<div style="padding: 15px; max-width: 800px; margin: auto;">
<div style="background: #f0f9ff; border: 1px solid #bae6fd; border-radius: 8px; padding: 16px; margin-bottom: 16px;">
<strong style="color: #0369a1;">Question:</strong>
<p style="font-size: 16px; line-height: 1.7; margin: 8px 0 0 0;">{{text}}</p>
</div>
<div style="background: #fefce8; border: 1px solid #fde68a; border-radius: 8px; padding: 16px; margin-bottom: 16px;">
<strong style="color: #a16207;">Options:</strong>
<ul style="font-size: 15px; line-height: 1.8; margin: 8px 0 0 0;">
<li><strong>A:</strong> {{option_a}}</li>
<li><strong>B:</strong> {{option_b}}</li>
<li><strong>C:</strong> {{option_c}}</li>
<li><strong>D:</strong> {{option_d}}</li>
</ul>
</div>
</div>
allow_all_users: true
instances_per_annotator: 50
annotation_per_instance: 2
allow_skip: true
skip_reason_required: false
Sample Datasample-data.json
[
{
"id": "brain_001",
"text": "A man pushes his car to a hotel and tells the owner he is bankrupt. Why?",
"option_a": "He lost all his money in a bet",
"option_b": "He is playing Monopoly",
"option_c": "His car broke down and he cannot afford repairs",
"option_d": "The hotel is actually a bank"
},
{
"id": "brain_002",
"text": "What can travel around the world while staying in a corner?",
"option_a": "A satellite",
"option_b": "A postage stamp",
"option_c": "A bird",
"option_d": "The wind"
}
]
// ... and 8 more itemsGet This Design
Clone or download from the repository
Quick start:
git clone https://github.com/davidjurgens/potato-showcase.git cd potato-showcase/semeval/2024/task09-brainteaser potato start config.yaml
Dataset & paper
Jiang et al., SemEval 2024
Citation (BibTeX)
@inproceedings{jiang-etal-2024-semeval,
title = "{S}em{E}val-2024 Task 9: {BRAINTEASER}: A Novel Task Defying Common Sense",
author = "Jiang, Yifan and Ilievski, Filip and Ma, Kaixin",
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
pages = "1994--2008",
doi = "10.18653/v1/2024.semeval-1.274",
url = "https://aclanthology.org/2024.semeval-1.274/"
}Details
Annotation Types
Domain
Use Cases
Tags
Found an issue or want to improve this design?
Open an IssueRelated Designs
Machine Comprehension Using Commonsense Knowledge
Multiple-choice reading comprehension requiring commonsense reasoning over narrative texts, selecting the best answer and providing reasoning. Based on SemEval-2018 Task 11.
Math Question Answering and Category Classification
Answering SAT-style mathematical questions with category classification, covering closed-vocabulary algebra, open-vocabulary algebra, and geometry. Based on SemEval-2019 Task 10 (Math QA).
QA over Tabular Data
Question answering over tabular data: annotators answer natural-language questions from a table by providing the value or list derived from it, and label the answer type (boolean, category, number, or list). Based on SemEval-2025 Task 8 (DataBench).