Lost in Translation: The Algorithmic Gap Between LMs and the Brain
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929410747138048 |
|---|---|
| author | Tosato, Tommaso Notsawo, Pascal Jr Tikeng Helbling, Saskia Rish, Irina Dumas, Guillaume |
| author_facet | Tosato, Tommaso Notsawo, Pascal Jr Tikeng Helbling, Saskia Rish, Irina Dumas, Guillaume |
| contents | Language Models (LMs) have achieved impressive performance on various linguistic tasks, but their relationship to human language processing in the brain remains unclear. This paper examines the gaps and overlaps between LMs and the brain at different levels of analysis, emphasizing the importance of looking beyond input-output behavior to examine and compare the internal processes of these systems. We discuss how insights from neuroscience, such as sparsity, modularity, internal states, and interactive learning, can inform the development of more biologically plausible language models. Furthermore, we explore the role of scaling laws in bridging the gap between LMs and human cognition, highlighting the need for efficiency constraints analogous to those in biological systems. By developing LMs that more closely mimic brain function, we aim to advance both artificial intelligence and our understanding of human cognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04680 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Lost in Translation: The Algorithmic Gap Between LMs and the Brain Tosato, Tommaso Notsawo, Pascal Jr Tikeng Helbling, Saskia Rish, Irina Dumas, Guillaume Neurons and Cognition Artificial Intelligence Computation and Language Language Models (LMs) have achieved impressive performance on various linguistic tasks, but their relationship to human language processing in the brain remains unclear. This paper examines the gaps and overlaps between LMs and the brain at different levels of analysis, emphasizing the importance of looking beyond input-output behavior to examine and compare the internal processes of these systems. We discuss how insights from neuroscience, such as sparsity, modularity, internal states, and interactive learning, can inform the development of more biologically plausible language models. Furthermore, we explore the role of scaling laws in bridging the gap between LMs and human cognition, highlighting the need for efficiency constraints analogous to those in biological systems. By developing LMs that more closely mimic brain function, we aim to advance both artificial intelligence and our understanding of human cognition. |
| title | Lost in Translation: The Algorithmic Gap Between LMs and the Brain |
| topic | Neurons and Cognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2407.04680 |