169 lines
11 KiB
BibTeX
169 lines
11 KiB
BibTeX
|
|
@Article{app14020744,
|
|
AUTHOR = {Testolin, Alberto},
|
|
TITLE = {Can Neural Networks Do Arithmetic? A Survey on the Elementary Numerical Skills of State-of-the-Art Deep Learning Models},
|
|
JOURNAL = {Applied Sciences},
|
|
VOLUME = {14},
|
|
YEAR = {2024},
|
|
NUMBER = {2},
|
|
ARTICLE-NUMBER = {744},
|
|
URL = {https://www.mdpi.com/2076-3417/14/2/744},
|
|
ISSN = {2076-3417},
|
|
ABSTRACT = {Creating learning models that can exhibit sophisticated reasoning abilities is one of the greatest challenges in deep learning research, and mathematics is rapidly becoming one of the target domains for assessing scientific progress in this direction. In the past few years there has been an explosion of neural network architectures, datasets, and benchmarks specifically designed to tackle mathematical problems, reporting impressive achievements in disparate fields such as automated theorem proving, numerical integration, and the discovery of new conjectures or matrix multiplication algorithms. However, despite this notable success it is still unclear whether deep learning models possess an elementary understanding of quantities and numbers. This survey critically examines the recent literature, concluding that even state-of-the-art architectures and large language models often fall short when probed with relatively simple tasks designed to test basic numerical and arithmetic knowledge.},
|
|
DOI = {10.3390/app14020744}
|
|
}
|
|
@article{Wang2024, title={History, development, and principles of large language models: An introductory survey}, DOI={10.1007/s43681-024-00583-7}, journal={AI and Ethics}, author={Wang, Zichong and Chu, Zhibo and Doan, Thang Viet and Ni, Shiwen and Yang, Min and Zhang, Wenbin}, year={2024}, month={Oct}}
|
|
@misc{vaswani2023attentionneed,
|
|
title={Attention Is All You Need},
|
|
author={Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin},
|
|
year={2023},
|
|
eprint={1706.03762},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/1706.03762},
|
|
}
|
|
|
|
@misc{ivanov2024,
|
|
title={AI Benchmarks and Datasets for LLM Evaluation},
|
|
author={Todor Ivanov and Valeri Penchev},
|
|
year={2024},
|
|
eprint={2412.01020},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.DC},
|
|
url={https://arxiv.org/abs/2412.01020},
|
|
}
|
|
@misc{hoffmann2022trainingcomputeoptimallargelanguage,
|
|
title={Training Compute-Optimal Large Language Models},
|
|
author={Jordan Hoffmann and Sebastian Borgeaud and Arthur Mensch and Elena Buchatskaya and Trevor Cai and Eliza Rutherford and Diego de Las Casas and Lisa Anne Hendricks and Johannes Welbl and Aidan Clark and Tom Hennigan and Eric Noland and Katie Millican and George van den Driessche and Bogdan Damoc and Aurelia Guy and Simon Osindero and Karen Simonyan and Erich Elsen and Jack W. Rae and Oriol Vinyals and Laurent Sifre},
|
|
year={2022},
|
|
eprint={2203.15556},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/2203.15556},
|
|
}
|
|
@misc{hendrycks2021measuringmathematicalproblemsolving,
|
|
title={Measuring Mathematical Problem Solving With the MATH Dataset},
|
|
author={Dan Hendrycks and Collin Burns and Saurav Kadavath and Akul Arora and Steven Basart and Eric Tang and Dawn Song and Jacob Steinhardt},
|
|
year={2021},
|
|
eprint={2103.03874},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.LG},
|
|
url={https://arxiv.org/abs/2103.03874},
|
|
}
|
|
|
|
@article{hendrycksmath2021,
|
|
title={Measuring Mathematical Problem Solving With the MATH Dataset},
|
|
author={Dan Hendrycks and Collin Burns and Saurav Kadavath and Akul Arora and Steven Basart and Eric Tang and Dawn Song and Jacob Steinhardt},
|
|
journal={NeurIPS},
|
|
year={2021}
|
|
}
|
|
|
|
@misc{ahn2024largelanguagemodelsmathematical,
|
|
title={Large Language Models for Mathematical Reasoning: Progresses and Challenges},
|
|
author={Janice Ahn and Rishu Verma and Renze Lou and Di Liu and Rui Zhang and Wenpeng Yin},
|
|
year={2024},
|
|
eprint={2402.00157},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/2402.00157},
|
|
}
|
|
@misc{cobbe2021trainingverifierssolvemath,
|
|
title={Training Verifiers to Solve Math Word Problems},
|
|
author={Karl Cobbe and Vineet Kosaraju and Mohammad Bavarian and Mark Chen and Heewoo Jun and Lukasz Kaiser and Matthias Plappert and Jerry Tworek and Jacob Hilton and Reiichiro Nakano and Christopher Hesse and John Schulman},
|
|
year={2021},
|
|
eprint={2110.14168},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.LG},
|
|
url={https://arxiv.org/abs/2110.14168},
|
|
}
|
|
@misc{cuda_programming_guide_2025,
|
|
author = {NVIDIA},
|
|
title = {1. Introduction - CUDA C++ Programming Guide},
|
|
year = {2025},
|
|
month = {Feb},
|
|
url = {https://docs.nvidia.com/cuda/cuda-c-programming-guide/},
|
|
journal = {1. Introduction - CUDA C++ Programming Guide}
|
|
}
|
|
@misc{deepseekai2025deepseekv3technicalreport,
|
|
title={DeepSeek-V3 Technical Report},
|
|
author={DeepSeek-AI and Aixin Liu and Bei Feng and Bing Xue and Bingxuan Wang and Bochao Wu and Chengda Lu and Chenggang Zhao and Chengqi Deng and Chenyu Zhang and Chong Ruan and Damai Dai and Daya Guo and Dejian Yang and Deli Chen and Dongjie Ji and Erhang Li and Fangyun Lin and Fucong Dai and Fuli Luo and Guangbo Hao and Guanting Chen and Guowei Li and H. Zhang and Han Bao and Hanwei Xu and Haocheng Wang and Haowei Zhang and Honghui Ding and Huajian Xin and Huazuo Gao and Hui Li and Hui Qu and J. L. Cai and Jian Liang and Jianzhong Guo and Jiaqi Ni and Jiashi Li and Jiawei Wang and Jin Chen and Jingchang Chen and Jingyang Yuan and Junjie Qiu and Junlong Li and Junxiao Song and Kai Dong and Kai Hu and Kaige Gao and Kang Guan and Kexin Huang and Kuai Yu and Lean Wang and Lecong Zhang and Lei Xu and Leyi Xia and Liang Zhao and Litong Wang and Liyue Zhang and Meng Li and Miaojun Wang and Mingchuan Zhang and Minghua Zhang and Minghui Tang and Mingming Li and Ning Tian and Panpan Huang and Peiyi Wang and Peng Zhang and Qiancheng Wang and Qihao Zhu and Qinyu Chen and Qiushi Du and R. J. Chen and R. L. Jin and Ruiqi Ge and Ruisong Zhang and Ruizhe Pan and Runji Wang and Runxin Xu and Ruoyu Zhang and Ruyi Chen and S. S. Li and Shanghao Lu and Shangyan Zhou and Shanhuang Chen and Shaoqing Wu and Shengfeng Ye and Shengfeng Ye and Shirong Ma and Shiyu Wang and Shuang Zhou and Shuiping Yu and Shunfeng Zhou and Shuting Pan and T. Wang and Tao Yun and Tian Pei and Tianyu Sun and W. L. Xiao and Wangding Zeng and Wanjia Zhao and Wei An and Wen Liu and Wenfeng Liang and Wenjun Gao and Wenqin Yu and Wentao Zhang and X. Q. Li and Xiangyue Jin and Xianzu Wang and Xiao Bi and Xiaodong Liu and Xiaohan Wang and Xiaojin Shen and Xiaokang Chen and Xiaokang Zhang and Xiaosha Chen and Xiaotao Nie and Xiaowen Sun and Xiaoxiang Wang and Xin Cheng and Xin Liu and Xin Xie and Xingchao Liu and Xingkai Yu and Xinnan Song and Xinxia Shan and Xinyi Zhou and Xinyu Yang and Xinyuan Li and Xuecheng Su and Xuheng Lin and Y. K. Li and Y. Q. Wang and Y. X. Wei and Y. X. Zhu and Yang Zhang and Yanhong Xu and Yanhong Xu and Yanping Huang and Yao Li and Yao Zhao and Yaofeng Sun and Yaohui Li and Yaohui Wang and Yi Yu and Yi Zheng and Yichao Zhang and Yifan Shi and Yiliang Xiong and Ying He and Ying Tang and Yishi Piao and Yisong Wang and Yixuan Tan and Yiyang Ma and Yiyuan Liu and Yongqiang Guo and Yu Wu and Yuan Ou and Yuchen Zhu and Yuduan Wang and Yue Gong and Yuheng Zou and Yujia He and Yukun Zha and Yunfan Xiong and Yunxian Ma and Yuting Yan and Yuxiang Luo and Yuxiang You and Yuxuan Liu and Yuyang Zhou and Z. F. Wu and Z. Z. Ren and Zehui Ren and Zhangli Sha and Zhe Fu and Zhean Xu and Zhen Huang and Zhen Zhang and Zhenda Xie and Zhengyan Zhang and Zhewen Hao and Zhibin Gou and Zhicheng Ma and Zhigang Yan and Zhihong Shao and Zhipeng Xu and Zhiyu Wu and Zhongyu Zhang and Zhuoshu Li and Zihui Gu and Zijia Zhu and Zijun Liu and Zilin Li and Ziwei Xie and Ziyang Song and Ziyi Gao and Zizheng Pan},
|
|
year={2025},
|
|
eprint={2412.19437},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/2412.19437},
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@article{hendrycksmath2021,
|
|
title={Measuring Mathematical Problem Solving With the MATH Dataset},
|
|
author={Dan Hendrycks and Collin Burns and Saurav Kadavath and Akul Arora and Steven Basart and Eric Tang and Dawn Song and Jacob Steinhardt},
|
|
journal={NeurIPS},
|
|
year={2021}
|
|
}
|
|
|
|
@misc{besiroglu2024chinchillascalingreplicationattempt,
|
|
title={Chinchilla Scaling: A replication attempt},
|
|
author={Tamay Besiroglu and Ege Erdil and Matthew Barnett and Josh You},
|
|
year={2024},
|
|
eprint={2404.10102},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.AI},
|
|
url={https://arxiv.org/abs/2404.10102},
|
|
}
|
|
|
|
@misc{ahn2024largelanguagemodelsmathematical,
|
|
title={Large Language Models for Mathematical Reasoning: Progresses and Challenges},
|
|
author={Janice Ahn and Rishu Verma and Renze Lou and Di Liu and Rui Zhang and Wenpeng Yin},
|
|
year={2024},
|
|
eprint={2402.00157},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/2402.00157},
|
|
}
|
|
@misc{besold2017neuralsymboliclearningreasoningsurvey,
|
|
title={Neural-Symbolic Learning and Reasoning: A Survey and Interpretation},
|
|
author={Tarek R. Besold and Artur d'Avila Garcez and Sebastian Bader and Howard Bowman and Pedro Domingos and Pascal Hitzler and Kai-Uwe Kuehnberger and Luis C. Lamb and Daniel Lowd and Priscila Machado Vieira Lima and Leo de Penning and Gadi Pinkas and Hoifung Poon and Gerson Zaverucha},
|
|
year={2017},
|
|
eprint={1711.03902},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.AI},
|
|
url={https://arxiv.org/abs/1711.03902},
|
|
}
|
|
@misc{petruzzellis2024assessingemergentsymbolicreasoning,
|
|
title={Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models},
|
|
author={Flavio Petruzzellis and Alberto Testolin and Alessandro Sperduti},
|
|
year={2024},
|
|
eprint={2406.06588},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/2406.06588},
|
|
}
|
|
@misc{xu2024chatglmmathimprovingmathproblemsolving,
|
|
title={ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline},
|
|
author={Yifan Xu and Xiao Liu and Xinghan Liu and Zhenyu Hou and Yueyan Li and Xiaohan Zhang and Zihan Wang and Aohan Zeng and Zhengxiao Du and Wenyi Zhao and Jie Tang and Yuxiao Dong},
|
|
year={2024},
|
|
eprint={2404.02893},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/2404.02893},
|
|
}
|
|
@misc{gao2023palprogramaidedlanguagemodels,
|
|
title={PAL: Program-aided Language Models},
|
|
author={Luyu Gao and Aman Madaan and Shuyan Zhou and Uri Alon and Pengfei Liu and Yiming Yang and Jamie Callan and Graham Neubig},
|
|
year={2023},
|
|
eprint={2211.10435},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CL},
|
|
url={https://arxiv.org/abs/2211.10435},
|
|
}
|
|
|