Papers › MuSiQue: Multihop Questions via Single-hop Question Composition

MuSiQue: Multihop Questions via Single-hop Question Composition

2 Aug 2021arXiv:2108.00573archive 2025-07-28

Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal

Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by construction, \emph{requires} proper multihop reasoning? To this end, we introduce a bottom-up approach that systematically selects composable pairs of single-hop questions that are connected, i.e., where one reasoning step critically relies on information from another. This bottom-up methodology lets us explore a vast space of questions and add stringent filters as well as other mechanisms targeting connected reasoning. It provides fine-grained control over the construction process and the properties of the resulting k-hop questions. We use this methodology to create MuSiQue-Ans, a new multihop QA dataset with 25K 2-4 hop questions. Relative to existing datasets, MuSiQue-Ans is more difficult overall (3x increase in human-machine gap), and harder to cheat via disconnected reasoning (e.g., a single-hop model has a 30 point drop in F1). We further add unanswerable contrast questions to produce a more stringent dataset, MuSiQue-Full. We hope our datasets will help the NLP community develop models that perform genuine multihop reasoning.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2108.00573")

Code

Syntology Ran 1 of 16 code samples harvested from 2 repositories linked to this paper; 15 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 15 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

stonybrooknlp/musique officialmentioned in papermentioned on GitHub report
Bodoral/MuSiQue_replication mentioned on GitHubnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
mangopy/direct-rag-learning mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested; 1 ran; 0 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
15unverified

Licence: 1 of the 16 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

read_jsonl stonybrooknlp/musique/evaluate_v1.0.py official repository ran · our draft was wrong CC-BY-4.0 · pointer only · a0c3c47032ca66fd · report
cal_ppl mangopy/direct-rag-learning/src/prepare/entropy.py community (archive-listed) unverified Apache-2.0 (permissive) · ebfd9b0ec5f4b3ef · report
causal_cross_entropy mangopy/direct-rag-learning/src/prepare/entropy.py community (archive-listed) unverified Apache-2.0 (permissive) · fac0d9d6ff56e2b2 · report
collect_docs mangopy/direct-rag-learning/src/evaluate.py community (archive-listed) unverified Apache-2.0 (permissive) · 9369e71b95149aa5 · report
document_retrieval mangopy/direct-rag-learning/src/prepare/prepare.py community (archive-listed) unverified Apache-2.0 (permissive) · 4a62a7015c03e433 · report
eval_em mangopy/direct-rag-learning/src/utilize/metrics.py community (archive-listed) unverified Apache-2.0 (permissive) · 0b2979a7d1760cb1 · report
gather_data mangopy/direct-rag-learning/src/prepare/prepare.py community (archive-listed) unverified Apache-2.0 (permissive) · 4e8dbe891b051948 · report
generation_instruction mangopy/direct-rag-learning/src/instruction.py community (archive-listed) unverified Apache-2.0 (permissive) · bec7c35aef9d72d5 · report
get_command mangopy/direct-rag-learning/src/prepare/sampling.py community (archive-listed) unverified Apache-2.0 (permissive) · a54293fda5579b8c · report
launch mangopy/direct-rag-learning/src/evaluate.py community (archive-listed) unverified Apache-2.0 (permissive) · bb3452c00b70772e · report
normalize_answer mangopy/direct-rag-learning/src/utilize/metrics.py community (archive-listed) unverified Apache-2.0 (permissive) · 97cb57dd2386abcb · report
prepare_warmup_data_for_generation mangopy/direct-rag-learning/src/prepare/prepare.py community (archive-listed) unverified Apache-2.0 (permissive) · ae22245c5794b39a · report
preprocess_supervised_dataset mangopy/direct-rag-learning/src/prepare/entropy.py community (archive-listed) unverified Apache-2.0 (permissive) · 9b674a8aeb03a2f2 · report
rank_instruction mangopy/direct-rag-learning/src/instruction.py community (archive-listed) unverified Apache-2.0 (permissive) · 203ee66a16f129c1 · report
rounder mangopy/direct-rag-learning/src/utilize/metrics.py community (archive-listed) unverified Apache-2.0 (permissive) · 1ac4537f9c4bf017 · report
shell_command mangopy/direct-rag-learning/src/evaluate.py community (archive-listed) unverified Apache-2.0 (permissive) · 456d16436e8dcb49 · report

Tasks

Multi-hop Question AnsweringQuestion Answering

Datasets

Introduced by this paper, per the archive.

MuSiQue-Ans

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections