Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2502.17304 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916627927269376 |
|---|---|
| author | Sauerland, Uli Matthaei, Celia Salfner, Felix |
| author_facet | Sauerland, Uli Matthaei, Celia Salfner, Felix |
| contents | We argue that human language learning proceeds in a manner that is different in nature from current approaches to training LLMs, predicting a difference in learning biases. We then present evidence from German plural formation by LLMs that confirm our hypothesis that even very powerful implementations produce results that miss aspects of the logic inherent to language that humans have no problem with. We conclude that attention to the different structures of human language and artificial neural networks is likely to be an avenue to improve LLM performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17304 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Child vs. machine language learning: Can the logical structure of human language unleash LLMs? Sauerland, Uli Matthaei, Celia Salfner, Felix Computation and Language Artificial Intelligence We argue that human language learning proceeds in a manner that is different in nature from current approaches to training LLMs, predicting a difference in learning biases. We then present evidence from German plural formation by LLMs that confirm our hypothesis that even very powerful implementations produce results that miss aspects of the logic inherent to language that humans have no problem with. We conclude that attention to the different structures of human language and artificial neural networks is likely to be an avenue to improve LLM performance. |
| title | Child vs. machine language learning: Can the logical structure of human language unleash LLMs? |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.17304 |