Case-Based or Rule-Based: How Do Transformers Do the Math?

1 code implementation • 27 Feb 2024 • Yi Hu, Xiaojuan Tang, Haotong Yang, Muhan Zhang

Through carefully designed intervention experiments on five math tasks, we confirm that transformers are performing case-based reasoning, no matter whether scratchpad is used, which aligns with the previous observations that transformers use subgraph matching/shortcut learning to reason.

Math Systematic Generalization

Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners

1 code implementation • 24 May 2023 • Xiaojuan Tang, Zilong Zheng, Jiaqi Li, Fanxu Meng, Song-Chun Zhu, Yitao Liang, Muhan Zhang

On the whole, our analysis provides a novel perspective on the role of semantics in developing and evaluating language models' reasoning abilities.

RulE: Neural-Symbolic Knowledge Graph Reasoning with Rule Embedding

1 code implementation • 24 Oct 2022 • Xiaojuan Tang, Song-Chun Zhu, Yitao Liang, Muhan Zhang

In this paper, we propose a novel and principled framework called \textbf{RulE} (stands for {Rul}e {E}mbedding) to effectively leverage logical rules to enhance KG reasoning.

Knowledge Graph Embedding Knowledge Graphs +1