Papers › Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem

Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem

21 Oct 2022arXiv:2210.11694archive 2025-07-28

Wenqi Zhang, Yongliang Shen, Yanna Ma, Xiaoxia Cheng, Zeqi Tan, Qingpeng Nong, Weiming Lu

Math word problem solver requires both precise relation reasoning about quantities in the text and reliable generation for the diverse equation. Current sequence-to-tree or relation extraction methods regard this only from a fixed view, struggling to simultaneously handle complex semantics and diverse equations. However, human solving naturally involves two consistent reasoning views: top-down and bottom-up, just as math equations also can be expressed in multiple equivalent forms: pre-order and post-order. We propose a multi-view consistent contrastive learning for a more complete semantics-to-equation mapping. The entire process is decoupled into two independent but consistent views: top-down decomposition and bottom-up construction, and the two reasoning views are aligned in multi-granularity for consistency, enhancing global generation and precise reasoning. Experiments on multiple datasets across two languages show our approach significantly outperforms the existing baselines, especially on complex problems. We also show after consistent alignment, multi-view can absorb the merits of both views and generate more diverse results consistent with the mathematical laws.

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="2210.11694")

Code

Syntology Ran 1 of 13 code samples harvested from 1 repository linked to this paper; 12 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 13 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zwq2018/multi-view-consistency-for-mwp officialmentioned in papermentioned on GitHubpytorchMIT 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

13 samples harvested; 1 ran; 0 honoured the contract we drafted; 12 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
12unverified

Licence: 0 of the 13 samples are 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 zwq2018/multi-view-consistency-for-mwp. “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_data zwq2018/multi-view-consistency-for-mwp/src/utils.py official repository ran · our draft was wrong MIT (permissive) · 2f69ddcd06d5421f · report
compute zwq2018/multi-view-consistency-for-mwp/src/eval/utils.py official repository unverified MIT (permissive) · 6cca9d6a936ecfcc · report
compute_value zwq2018/multi-view-consistency-for-mwp/src/eval/utils.py official repository unverified MIT (permissive) · 01d6defe25112d21 · report
compute_value_for_incremental_equations zwq2018/multi-view-consistency-for-mwp/src/eval/utils.py official repository unverified MIT (permissive) · 360275f90909519f · report
copy_list zwq2018/multi-view-consistency-for-mwp/src/model/tree_decoder.py official repository unverified MIT (permissive) · 2f2e884c6e5f1525 · report
get_batched_prediction_consider_multiple_m0 zwq2018/multi-view-consistency-for-mwp/main_math23k.py official repository unverified MIT (permissive) · 6f6a7869a7797e21 · report
get_combination_mask zwq2018/multi-view-consistency-for-mwp/src/model/universal_model.py official repository unverified MIT (permissive) · dc88195e78925e47 · report
have_constant zwq2018/multi-view-consistency-for-mwp/preprocess/process_math23k.py official repository unverified MIT (permissive) · 68123269a97bdff9 · report
have_pi zwq2018/multi-view-consistency-for-mwp/preprocess/process_math23k.py official repository unverified MIT (permissive) · 87b16c0cfd687a02 · report
have_square zwq2018/multi-view-consistency-for-mwp/preprocess/process_math23k.py official repository unverified MIT (permissive) · e06f898b70a977ff · report
masked_cross_entropy zwq2018/multi-view-consistency-for-mwp/src/model/tree_decoder.py official repository unverified MIT (permissive) · 80f5fed9c34adca3 · report
parse_arguments zwq2018/multi-view-consistency-for-mwp/main_math23k.py official repository unverified MIT (permissive) · aa868b456e259fdc · report
sequence_mask zwq2018/multi-view-consistency-for-mwp/src/model/tree_decoder.py official repository unverified MIT (permissive) · e966aac70ae27f8f · report

Tasks

Contrastive LearningMathMath Word Problem SolvingMathematical ReasoningRelation Extraction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Math Word Problem Solving MAWPS Multi-view Accuracy (%) 92.3 #4 of 25 Archive leaderboard report
Math Word Problem Solving Math23K Multi-view* (ours) Accuracy (5-fold) 85.2 #2 of 19 Archive leaderboard report
Math Word Problem Solving Math23K Multi-view* (ours) Accuracy (training-test) 87.1 #2 of 19 Archive leaderboard report
Math Word Problem Solving MathQA Multi-view Answer Accuracy 80.6 #3 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive Learning

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