Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Solving Math Word Problems with Teacher Supervision
Authors: Zhenwen Liang, Xiangliang Zhang
IJCAI 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on two benchmark MWPs datasets verified that our proposed solution outperforms the state-of-the-art models. |
| Researcher Affiliation | Academia | King Abdullah University of Science and Technology (KAUST), Saudi Arabia |
| Pseudocode | Yes | Algorithm 1 Negative Answer Generation |
| Open Source Code | Yes | Our code in Python with Pytorch framework can be found at https://github.com/derderking/MWP-teacher. |
| Open Datasets | Yes | We take two widely used benchmark datasets for the experimental evaluation, Math23K and MAWPS. Math23k [Wang et al., 2017] is one of the most commonly used dataset for MWP solver evaluation. It has 23161 math word problems. MAWPS [Koncel-Kedziorski et al., 2016] is a relatively small dataset which only contains 2373 problems. |
| Dataset Splits | Yes | There are also others using a 5-fold cross validation to measure the performance of their solvers. In our experiments, we report the accuracy for both settings. We also perform 5-fold cross validation on this dataset. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for experiments, such as GPU models, CPU specifications, or memory. |
| Software Dependencies | No | The paper mentions "Our code in Python with Pytorch framework" but does not specify version numbers for Python, Pytorch, or any other libraries used, which is required for reproducibility. |
| Experiment Setup | Yes | The embedding dimension of Wembed is set to 128. The latent feature dimension d is set to 512. Our models are trained for 120 epochs. The training was conducted in two stages. We use Adam optimizer [Kingma and Ba, 2014] with initial learning rate 0.001, which is halved every 30 epochs. Dropout [Hinton et al., 2012] on embedding matrix of probability 0.5 is employed to prevent overfitting. During testing, we use beam search of size 8 to generate the math expression sequence. The weight α in Eq. (7) is set to 0.1, by its sensitivity analysis. |