PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914815795003392 |
|---|---|
| author | Xu, Fangzhi Lin, Qika Zhao, Tianzhe Han, Jiawei Liu, Jun |
| author_facet | Xu, Fangzhi Lin, Qika Zhao, Tianzhe Han, Jiawei Liu, Jun |
| contents | Logical reasoning task has attracted great interest since it was proposed. Faced with such a task, current competitive models, even large language models (e.g., ChatGPT and PaLM 2), still perform badly. Previous promising LMs struggle in logical consistency modeling and logical structure perception. To this end, we model the logical reasoning task by transforming each logical sample into reasoning paths and propose an architecture \textbf{PathReasoner}. It addresses the task from the views of both data and model. To expand the diversity of the logical samples, we propose an atom extension strategy supported by equivalent logical formulas, to form new reasoning paths. From the model perspective, we design a stack of transformer-style blocks. In particular, we propose a path-attention module to joint model in-atom and cross-atom relations with the high-order diffusion strategy. Experiments show that PathReasoner achieves competitive performances on two logical reasoning benchmarks and great generalization abilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19109 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering Xu, Fangzhi Lin, Qika Zhao, Tianzhe Han, Jiawei Liu, Jun Computation and Language Logical reasoning task has attracted great interest since it was proposed. Faced with such a task, current competitive models, even large language models (e.g., ChatGPT and PaLM 2), still perform badly. Previous promising LMs struggle in logical consistency modeling and logical structure perception. To this end, we model the logical reasoning task by transforming each logical sample into reasoning paths and propose an architecture \textbf{PathReasoner}. It addresses the task from the views of both data and model. To expand the diversity of the logical samples, we propose an atom extension strategy supported by equivalent logical formulas, to form new reasoning paths. From the model perspective, we design a stack of transformer-style blocks. In particular, we propose a path-attention module to joint model in-atom and cross-atom relations with the high-order diffusion strategy. Experiments show that PathReasoner achieves competitive performances on two logical reasoning benchmarks and great generalization abilities. |
| title | PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.19109 |