Benchmarking ChatGPT on Algorithmic Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916209650302976 |
|---|---|
| author | McLeish, Sean Schwarzschild, Avi Goldstein, Tom |
| author_facet | McLeish, Sean Schwarzschild, Avi Goldstein, Tom |
| contents | We evaluate ChatGPT's ability to solve algorithm problems from the CLRS benchmark suite that is designed for GNNs. The benchmark requires the use of a specified classical algorithm to solve a given problem. We find that ChatGPT outperforms specialist GNN models, using Python to successfully solve these problems. This raises new points in the discussion about learning algorithms with neural networks and how we think about what out of distribution testing looks like with web scale training data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03441 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Benchmarking ChatGPT on Algorithmic Reasoning McLeish, Sean Schwarzschild, Avi Goldstein, Tom Artificial Intelligence Computation and Language Machine Learning We evaluate ChatGPT's ability to solve algorithm problems from the CLRS benchmark suite that is designed for GNNs. The benchmark requires the use of a specified classical algorithm to solve a given problem. We find that ChatGPT outperforms specialist GNN models, using Python to successfully solve these problems. This raises new points in the discussion about learning algorithms with neural networks and how we think about what out of distribution testing looks like with web scale training data. |
| title | Benchmarking ChatGPT on Algorithmic Reasoning |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2404.03441 |