Neural symbolic reasoning

I believe the neural symbolic approach is the only way to realize truthworthy reasoning, thus achieving true intelligence.

Here are some useful cases of the neural symbolic approach. And I think the role of a neural-symbolic engine will become much more important in the near future.

Synthesizing high-quality, verifiably correct reasoning steps on solving math problems. (Li et al., 2024).
Improving the autoformalization, a fundamental math capability of a neural model, through a hybrid neural-symbolic solution. (Li et al., 2024).

References

2024

NeurIPS

Neuro-Symbolic Data Generation for Math Reasoning

Zenan Li, and 7 more authors

In Advances in Neural Information Processing Systems, NeurIPS, 2024

Bib HTML

@inproceedings{NEURIPS2024_NSMR,
  title = {Neuro-Symbolic Data Generation for Math Reasoning},
  author = {Li, Zenan and Zhou, Zhi and Yao, Yuan and Zhang, Xian and Li, Yu-Feng and Cao, Chun and Yang, Fan and Ma, Xiaoxing},
  year = {2024},
  booktitle = {Advances in Neural Information Processing Systems, {NeurIPS}},
}

NeurIPS

Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency

Zenan Li, and 6 more authors

In Advances in Neural Information Processing Systems, NeurIPS, 2024

Bib HTML

@inproceedings{NEURIPS2024_AutoFormalization,
  title = {Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency},
  author = {Li, Zenan and Wu, Yifan and Li, Zhaoyu and Wei, Xinming and Zhang, Xian and Yang, Fan and Ma, Xiaoxing},
  year = {2024},
  booktitle = {Advances in Neural Information Processing Systems, {NeurIPS}},
}