List your company
ResearchFormerly WizWand

Math Word Problem Solving on Math23K (test)

87.1AccuracyMulti-view
53.50862.22970.9579.671Jul 3, 2021Nov 18, 2021Apr 6, 2022Aug 23, 2022Jan 9, 2023May 28, 2023Oct 14, 2023
Updated 8mo ago

Evaluation results

MethodLinks
Multi-viewCategory=Consistent Multi-View Learning, Pre-trained language model=true2022.1087.1
Ana-CLModel Category=Seq2Seq/Tree2023.1085.6
M-ViewModel Category=Seq2Exp2023.1085.6
Gen&RankPre-training architecture=Seq2Seq pre-train2021.0785.4
Gen-RankCategory=Seq2Seq, Pre-trained language model=true2022.1085.4
RE-DeductionCategory=I-RE, Pre-trained language model=true2022.1085.4
RankModel Category=Seq2Seq/Tree, reproduced=true2023.1085.4
RE-ExtModel Category=Seq2Exp2023.1085.4
Generate & Ranktraining=multi-task training2021.0985.4
Textual-CLModel Category=Seq2Seq/Tree2023.1085
ElasticModel Category=Seq2Exp, reproduced=true2023.1084.8
MWP-BERTPre-training architecture=Encoder pre-train, Pre-training=MWP pre-training and fine-tuning2021.0784.7
MWP-RoBERTaPre-training architecture=Encoder pre-train, Pre-training=MWP pre-training and fine-tuning2021.0784.5
BERT-TreeCategory=Structure-Gen, Pre-trained language model=true2022.1084.4
BERT-TModel Category=Seq2Seq/Tree2023.1084.4
MWP-NASModel Category=Seq2Exp2023.1084.4
RPKHS2021.0783.9
H-ReasonerCategory=Structure-Gen, Pre-trained language model=true2022.1083.9
H-ReasonerModel Category=Seq2Seq/Tree2023.1083.9
BERTPre-training architecture=Encoder pre-train, Pre-training=None2021.0783.8
RoBERTaPre-training architecture=Encoder pre-train, Pre-training=None2021.0783.5
Logic-DecModel Category=Seq2Seq/Tree2023.1083.4
BERT-CLPre-training architecture=Seq2Seq pre-train2021.0783.2
CL-PrototypeCategory=CL-Gen, Pre-trained language model=true2022.1083.2
PrototypeModel Category=Seq2Seq/Tree2023.1083.2
M-TreeModel Category=Seq2Exp2023.1082.5
REAL2021.0982.3
REALPre-training architecture=Seq2Seq pre-train2021.0782.3
mBARTtraining=fine-tuning2021.0980.8
T-DisCategory=CL-Gen, Pre-trained language model=true2022.1079.1
T-DisModel Category=Seq2Seq/Tree2023.1079.1
E-PointerModel Category=Seq2Exp, reproduced=true2023.1078.7
EEH-G2T2021.0778.5
Multi-E/D2021.0978.4
NumS2T2021.0778.1
DAGCategory=I-RE, Pre-trained language model=true2022.1077.5
DAGModel Category=Seq2Exp2023.1077.5
TSN-MD2021.0977.4
Graph2Tree2021.0977.4
Graph2Tree2021.0777.4
TSN-MD2021.0777.4
Graph2TreeCategory=Structure-Gen, Pre-trained language model=false2022.1077.4
G2TModel Category=Seq2Seq/Tree2023.1077.4
Graph2Tree2021.0977.4
RoGenCategory=Seq2Seq, Pre-trained language model=true2022.1076.9
PLM-GenModel Category=Seq2Seq/Tree2023.1076.9
BERTGenCategory=Seq2Seq, Pre-trained language model=true2022.1076.6
BERTGenModel Category=Seq2Seq/Tree2023.1076.6
KA-S2T2021.0776.3
NS-Solver2021.0775.7
NS-Solver2021.0775.67
GTS2021.0975.6
GTS2021.0775.6
GTSCategory=Structure-Gen, Pre-trained language model=false2022.1075.6
GTSModel Category=Seq2Seq/Tree2023.1075.6
GTS2021.0975.6
TSN-MD2021.0775.1
mBERTCategory=Seq2Seq, Pre-trained language model=true2022.1075.1
mBERTModel Category=Seq2Seq/Tree2023.1075.1
GTS2021.0774.3
GroupAttnCategory=Seq2Seq, Pre-trained language model=false2022.1069.5
GroupAttnModel Category=Seq2Seq/Tree2023.1069.5
Group-ATT2021.0969.5
AST-Dec2021.0969
T-RNN2021.0966.9
T-RNN2021.0966.9
Math-EN2021.0966.7
Math-EN2021.0766.7
Math-EN2021.0966.7
Self-ConsistencyModel Category=LLM, reproduced=true2023.1066.1
StackDecoder2021.0766
DNS2021.0758.1
gpt-3.5-turboModel Category=LLM, reproduced=true2023.1054.8