Everyday Knowledge Across Diverse Languages and Cultures (BLEnD)
SemEval-2026 Task 7: evaluating everyday cultural knowledge across diverse languages and cultures, built on the BLEnD benchmark. Annotators answer culturally grounded everyday-knowledge questions (e.g. common foods, customs, celebrations) for a given country/region. Two subtasks: Short Answer Questions (SAQ) and Multiple-Choice Questions (MCQ), covering many languages including low-resource ones.
Configuration Fileconfig.yaml
This Potato config reproduces the annotation task. Save it as config.yaml and run potato start config.yaml to try it.
# Everyday Knowledge Across Diverse Languages and Cultures (BLEnD)
# Based on Ousidhoum et al., SemEval-2026 Task 7
# Paper: https://aclanthology.org/2026.semeval-1.455/
# Task repo: https://github.com/BLEnD-SemEval2026/SemEval-2026-Task-7
# Underlying dataset: BLEnD (Myung et al., NeurIPS 2024) https://arxiv.org/abs/2406.09948
#
# The task probes everyday cultural knowledge (daily habits, customs,
# foods, celebrations) that is often shared within a culture but rarely
# written down. Questions are grounded in a specific country/region.
# Two subtasks:
# - Subtask 1 (SAQ): give the short free-text answer expected in that culture
# - Subtask 2 (MCQ): pick the correct option
# This showcase collects both a short answer and a multiple-choice answer,
# plus an optional applicability judgment.
annotation_task_name: "BLEnD - Everyday Cultural Knowledge"
task_dir: "."
data_files:
- sample-data.json
item_properties:
id_key: "id"
text_key: "question"
output_annotation_dir: "annotation_output/"
output_annotation_format: "json"
port: 8000
server_name: localhost
annotation_schemes:
- annotation_type: text
name: short_answer
description: "Subtask 1 (SAQ): the short answer most people in this culture would give"
textarea: false
required: false
placeholder: "Short answer..."
- annotation_type: radio
name: mcq_answer
description: "Subtask 2 (MCQ): select the correct option"
labels:
- "A"
- "B"
- "C"
- "D"
keyboard_shortcuts:
"A": "1"
"B": "2"
"C": "3"
"D": "4"
- annotation_type: radio
name: applicability
description: "Does this question have a clear culturally-shared answer for the given region?"
labels:
- "Yes"
- "No / varies too much"
annotation_instructions: |
Each item shows an everyday-knowledge question grounded in a specific
country or region, along with multiple-choice options. Provide the short
answer most people in that culture would give (Subtask 1), select the
correct multiple-choice option (Subtask 2), and indicate whether the
question has a clear culturally-shared answer.
html_layout: |
<div style="padding: 15px; max-width: 820px; margin: auto;">
<div style="background: #ecfeff; border: 1px solid #a5f3fc; border-radius: 8px; padding: 12px; margin-bottom: 10px;">
<strong style="color: #155e75;">Region:</strong>
<span style="margin-left: 8px;">{{region}}</span>
<span style="color:#64748b; margin-left: 12px;">Language: {{language}}</span>
</div>
<div style="background: #f0fdfa; border: 1px solid #99f6e4; border-radius: 8px; padding: 16px; margin-bottom: 8px;">
<strong style="color: #115e59;">Question:</strong>
<p style="font-size: 17px; line-height: 1.6; margin: 8px 0 0 0;">{{question}}</p>
</div>
<div style="color:#334155; font-size: 15px;">{{options}}</div>
</div>
allow_all_users: true
instances_per_annotator: 50
annotation_per_instance: 3
allow_skip: true
Sample Datasample-data.json
[
{
"id": "bln_001",
"region": "South Korea",
"language": "Korean",
"question": "What soup is traditionally eaten on New Year's Day to mark getting a year older?",
"options": "A) Tteokguk B) Miyeokguk C) Kimchi jjigae D) Samgyetang"
},
{
"id": "bln_002",
"region": "Mexico",
"language": "Spanish",
"question": "What bread is traditionally eaten around the Day of the Dead?",
"options": "A) Bolillo B) Pan de muerto C) Concha D) Telera"
}
]
// ... 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/2026/task07-blend-cultural-knowledge potato start config.yaml
Dataset & paper
Ousidhoum et al., SemEval 2026 (Task 7); built on BLEnD (Myung et al., NeurIPS 2024)
Citation (BibTeX)
@inproceedings{ousidhoum-etal-2026-semeval,
title = "{S}em{E}val-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures",
author = "Ousidhoum, Nedjma and Myung, Junho and Perez-Almendros, Carla and Jin, Jiho and Keleg, Amr and Beloucif, Meriem and Zhou, Yi and Agerri, Rodrigo and Araujo, Vladimir and Baes, Naomi and Barry, James and Boisson, Joanne and Chen, Nancy F. and de Kock, Christine and Edwards, Aleksandra and Fernandez de Landa, Joseba and Imam, Mohamed Fazli and Hakami, Huda and Hsieh, Shu-Kai and Imperial, Joseph Marvin and Lee, Roy Ka-Wei and Liu, Zhengyuan and Lyu, Chenyang and Samih, Younes and Sjons, Johan and Tan, Bryan and Ushio, Asahi and Zheng, Weihua and Oh, Alice and Camacho-Collados, Jose",
booktitle = "Proceedings of the 20th International Workshop on Semantic Evaluation (SemEval-2026)",
year = "2026",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.455",
pages = "3823--3837"
}
@inproceedings{myung2024blend,
title = "{BL}{E}n{D}: A Benchmark for {LLM}s on Everyday Knowledge in Diverse Cultures and Languages",
author = "Myung, Junho and Lee, Nayeon and Zhou, Yi and Jin, Jiho and Putri, Rifki Afina and Antypas, Dimosthenis and Borkakoty, Hsuvas and Kim, Eunsu and Perez-Almendros, Carla and Ayele, Abinew Ali and Guti{\'e}rrez-Basulto, V{\'i}ctor and Ib{\'a}{\~n}ez-Garc{\'i}a, Yazm{\'i}n and Lee, Hwaran and Muhammad, Shamsuddeen Hassan and Park, Kiwoong and Rzayev, Anar Sabuhi and White, Nina and Yimam, Seid Muhie and Pilehvar, Mohammad Taher and Ousidhoum, Nedjma and Camacho-Collados, Jose and Oh, Alice",
booktitle = "Advances in Neural Information Processing Systems 37 (NeurIPS 2024) Datasets and Benchmarks Track",
year = "2024",
url = "https://arxiv.org/abs/2406.09948"
}Details
Annotation Types
Domain
Use Cases
Tags
Found an issue or want to improve this design?
Open an IssueRelated Designs
EA-MT - Entity-Aware Machine Translation
Entity-aware machine translation evaluation requiring annotators to identify entity spans, classify translation errors, and provide corrected translations. Based on SemEval-2025 Task 2.
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).
CLARITY: Unmasking Political Question Evasions
SemEval-2026 Task 6 (CLARITY): detecting how directly a politician answers a question. Given a question-answer pair from a U.S. presidential interview, annotators classify the reply into one of three clarity levels (Clear Reply, Ambiguous, Clear Non-Reply) and, when the answer is evasive, identify the evasion technique used. Multi-part questions are first decomposed into single sub-questions so each judgment captures how well one specific inquiry is addressed.