Table · dataset · 2025
thunder-research-group/SNU_Ko-MuSR
Listed in Hugging Face Datasets
Dataset Card for SNU Ko-MuSR Dataset
Description
Summary
SNU Ko-MuSR is a Korean adaptation of MuSR, a benchmark designed to assess multistep reasoning abilities of large language models. It evaluates a model's ability to extract facts from long narratives, perform multi-step soft reasoning and deduce the conclusion according to the task settings. The benchmark consists of three subtasks: murder mysteries, object placements and team allocations, according to the MuSR benchmark.… See the full description on the dataset page: huggingface.co/datasets/thunder-research-group/SNU_Ko-MuSR.
Links
Get the data
- Hugging Face dataset page huggingface.co/datasets/thunder-research-group/SNU_Ko-MuSR ↗
Gated (auto) - request access on the dataset page
landing page · request access · from Hugging Face
Catalogue records · 1
- Hub API huggingface.co/api/datasets/thunder-research-group/SNU_Ko-MuSR ↗
metadata API · from Hugging Face
Topics
- Stated by source
- text
- From keywords
- Computer Science & AI
Provenance · 1 source records, 9 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Hugging Face Datasets | thunder-research-group/SNU_Ko-MuSR | 10 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · Hugging Face | connector:huggingface@1.0.0 | /gated |
| concepts[field].local:field:computer-science-ai | mapping · Hugging Face | connector:huggingface@1.0.0 | |
| concepts[modality].hf_modality:text | source · Hugging Face | connector:huggingface@1.0.0 | |
| created_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| description | source · Hugging Face | connector:huggingface@1.0.0 | /description |
| license | source · Hugging Face | connector:huggingface@1.0.0 | /tags[license:*] |
| publication_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| title | source · Hugging Face | connector:huggingface@1.0.0 | /id |
| updated_date | source · Hugging Face | connector:huggingface@1.0.0 |