paper-with-me

Math Word Problem Solving 벤치마크

Math Word Problem Solving on Math23K

76개 결과 · ⬇ CSV · JSON

Accuracy (5-fold)

64.7 72.1 79.5 86.9 94.3 2017-09 2026-11 Hybrid model w/ SNI — 64.7 (2017-09-01) Hybrid model w/ SNI — 64.7 (2017-09-01) Hybrid model w/ SNI — 64.7 (2017-09-01) Hybrid model w/ SNI — 64.7 (2017-09-01) GROUP-ATT — 66.9 (2019-07-01) GROUP-ATT — 66.9 (2019-07-01) GROUP-ATT — 66.9 (2019-07-01) GROUP-ATT — 66.9 (2019-07-01) GTS — 74.3 (2019-08-10) GTS — 74.3 (2019-08-10) GTS — 74.3 (2019-08-10) GTS — 74.3 (2019-08-10) Graph2Tree — 75.5 (2020-07-01) Graph2Tree — 75.5 (2020-07-01) Graph2Tree — 75.5 (2020-07-01) Graph2Tree — 75.5 (2020-07-01) SAU-Solver — 74.84 (2020-10-14) SAU-Solver — 74.84 (2020-10-14) SAU-Solver — 74.84 (2020-10-14) SAU-Solver — 74.84 (2020-10-14) MWP-BERT — 82.4 (2021-07-28) MWP-BERT — 82.4 (2021-07-28) MWP-BERT — 82.4 (2021-07-28) MWP-BERT — 82.4 (2021-07-28) RoBERTaGen — 76.6 (2021-09-02) RoBERTaGen — 76.6 (2021-09-02) RoBERTaGen — 76.6 (2021-09-02) RoBERTaGen — 76.6 (2021-09-02) Generate and Rank — 84.3 (2021-09-07) Generate and Rank — 84.3 (2021-09-07) Generate and Rank — 84.3 (2021-09-07) Generate and Rank — 84.3 (2021-09-07) Recall and Learn — 80.8 (2021-09-27) Recall and Learn — 80.8 (2021-09-27) Recall and Learn — 80.8 (2021-09-27) Recall and Learn — 80.8 (2021-09-27) Roberta-DeductReasoner — 83.0 (2022-03-19) Roberta-DeductReasoner — 83.0 (2022-03-19) Roberta-DeductReasoner — 83.0 (2022-03-19) Roberta-DeductReasoner — 83.0 (2022-03-19) Multi-view* (ours) — 85.2 (2022-10-21) Multi-view* (ours) — 85.2 (2022-10-21) Multi-view* (ours) — 85.2 (2022-10-21) Multi-view* (ours) — 85.2 (2022-10-21) Exp-Tree — 84.1 (2023-10-14) Exp-Tree — 84.1 (2023-10-14) Exp-Tree — 84.1 (2023-10-14) Exp-Tree — 84.1 (2023-10-14) GPT-4 (Teaching-Inspired) — 94.3 (2024-10-10) GPT-4 (Teaching-Inspired) — 94.3 (2024-10-10) GPT-4 (Teaching-Inspired) — 94.3 (2024-10-10) GPT-4 (Teaching-Inspired) — 94.3 (2024-10-10) Hybrid model w/ SNI — 64.7 (2017-09-01) GROUP-ATT — 66.9 (2019-07-01) GTS — 74.3 (2019-08-10) Graph2Tree — 75.5 (2020-07-01) MWP-BERT — 82.4 (2021-07-28) Generate and Rank — 84.3 (2021-09-07) Multi-view* (ours) — 85.2 (2022-10-21) GPT-4 (Teaching-Inspired) — 94.3 (2024-10-10)
RankModel Accuracy (5-fold)Accuracy (training-test)weakly-supervised Extra Training Data PaperCodeYear
1 GPT-4 (Teaching-Inspired) 94.3–– Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models sallytan13/teaching-inspired-prompting 2024
2 Multi-view* (ours) 85.287.1– ✓ Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem zwq2018/multi-view-consistency-for-mwp 2022
3 Generate and Rank 84.385.4– Generate & Rank: A Multi-task Framework for Math Word Problems 2021
4 Exp-Tree 84.186.2– An Expression Tree Decoding Strategy for Mathematical Equation Generation zwq2018/multi-view-consistency-for-mwp 2023
5 REAL2: Memory-augmented Solver 83.1885.2–
6 Roberta-DeductReasoner 83–– Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction allanj/deductive-mwp 2022
7 MWP-BERT 82.484.7– MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving lzhenwen/mwp-bert 2021
8 Recall and Learn 80.882.3– Recall and Learn: A Memory-augmented Solver for Math Word Problems sfeng-m/real4mwp 2021
9 RoBERTaGen 76.6–– MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers lyh-yf/mwptoolkit 2021
10 GTS w/ Data Augmentation 75.9––
11 Graph2Tree 75.577.4– Graph-to-Tree Learning for Solving Math Word Problems 2003pro/Graph2Tree 2020
12 SAU-Solver 74.84–– Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems QinJinghui/SAU-Solver 2020
13 GTS 74.3–– A Goal-Driven Tree-Structured Neural Model for Math Word Problems ShichaoSun/math_seq2tree 2019
14 GROUP-ATT 66.969.5– Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions lijierui/group-attention 2019
15 Hybrid model w/ SNI 64.7–– Deep Neural Solver for Math Word Problems 2017
16 ATHENA (roberta-large) –86.5– ATHENA: Mathematical Reasoning with Thought Expansion the-jb/athena-math 2023
17 ATHENA (roberta-base) –84.4– ATHENA: Mathematical Reasoning with Thought Expansion the-jb/athena-math 2023
18 T-RNN –66.9–
19 LBF ––59.8 Learning by Fixing: Solving Math Word Problems with Weak Supervision evelinehong/LBF 2020
20 GPT-4 (Teaching-Inspired) 94.3–– Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models sallytan13/teaching-inspired-prompting 2024
1–20 / 76 다음 → 페이지당 10 20 50 100