Minimization of Boolean Complexity in In-Context Concept Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912143328149504 |
|---|---|
| author | Wang, Leroy Z. McCoy, R. Thomas Steinert-Threlkeld, Shane |
| author_facet | Wang, Leroy Z. McCoy, R. Thomas Steinert-Threlkeld, Shane |
| contents | What factors contribute to the relative success and corresponding difficulties of in-context learning for Large Language Models (LLMs)? Drawing on insights from the literature on human concept learning, we test LLMs on carefully designed concept learning tasks, and show that task performance highly correlates with the Boolean complexity of the concept. This suggests that in-context learning exhibits a learning bias for simplicity in a way similar to humans. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02823 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Minimization of Boolean Complexity in In-Context Concept Learning Wang, Leroy Z. McCoy, R. Thomas Steinert-Threlkeld, Shane Computation and Language Artificial Intelligence What factors contribute to the relative success and corresponding difficulties of in-context learning for Large Language Models (LLMs)? Drawing on insights from the literature on human concept learning, we test LLMs on carefully designed concept learning tasks, and show that task performance highly correlates with the Boolean complexity of the concept. This suggests that in-context learning exhibits a learning bias for simplicity in a way similar to humans. |
| title | Minimization of Boolean Complexity in In-Context Concept Learning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2412.02823 |