$ open /benchmarks/musr▌discussed░░░░░░░░░░░░░░░░░░░░ 0/756 problems · discussed · posts
MuSR
Reasoning
MuSR poses multistep soft reasoning problems over algorithmically generated narratives. It has three domains — murder mysteries, object placements and team allocation — and this catalogue imports all three domains, 756 problems in total.
Zayne Sprague and collaborators introduced MuSR in 2023 to study multistep reasoning in narratives where individual clues require commonsense interpretation. The benchmark covered murder mysteries, object placement, and team allocation rather than relying only on explicitly stated logical rules. The catalogue lists TAUR-Lab as the source maintainer and records the Hugging Face dataset publication in May 2024.
How it was built
MuSR uses algorithmically generated narratives across three domains: murder mysteries, object placement and team allocation. Each problem presents a narrative, a question and candidate answers, while the reference data identifies the correct option. This catalogue records 250 problems in the murder-mystery selection and imports 200 of them, rather than representing all three domains.
At a glance
Metric
accuracy over the 250 problems in each domain
Size
756 problems imported across the three domain files (murder mysteries, object placements and team allocation).
License
cc-by-4.0 (declared on the Hugging Face dataset card)
Released
Dataset published on Hugging Face 2024-05
Maintainer
TAUR-Lab (source organisation)
Answer access
Columns outside the prompt allowlist, including any answer or reference solution, are separated into restricted storage and never rendered.
What a problem looks like
A narrative of several hundred words, a question about it, and the candidate answers as a list. The correct index is not part of the prompt.
The source ships the answer index and the chosen option; this catalogue keeps both in restricted storage and never renders them.
Metric: accuracy over the 250 problems in each domain
Why it is hard
The clues are spread through a long narrative and none of them decides the answer alone. The chain has to be assembled from commonsense inferences that the text never states.
Limitations and criticism
The generated narratives provide a controlled setting but do not establish performance on unrestricted real-world reasoning. Multiple-choice accuracy measures selection of the reference option without directly verifying the reasoning used to reach it. The murder-mystery selection also cannot substitute for an aggregate across object placement and team allocation, whose reasoning demands differ.
@article{sprague2023musr,
title={MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning},
author={Zayne Sprague and Xi Ye and Kaj Bostrom and Swarat Chaudhuri and Greg Durrett},
journal={arXiv preprint arXiv:2310.16049},
year={2023}
}
Related benchmarks
Discussion
1 thread and 0 posts on this page. Anyone may reply; no account is required.
Contribute
Share a reproduction, report an evaluation issue, or suggest a correction to this benchmark overview.