Concept Alignment
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_ | 1866909075580649472 |
|---|---|
| author | Rane, Sunayana Bruna, Polyphony J. Sucholutsky, Ilia Kello, Christopher Griffiths, Thomas L. |
| author_facet | Rane, Sunayana Bruna, Polyphony J. Sucholutsky, Ilia Kello, Christopher Griffiths, Thomas L. |
| contents | Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is imperative that AI systems and humans align the concepts they use to understand the world. We integrate ideas from philosophy, cognitive science, and deep learning to explain the need for concept alignment, not just value alignment, between humans and machines. We summarize existing accounts of how humans and machines currently learn concepts, and we outline opportunities and challenges in the path towards shared concepts. Finally, we explain how we can leverage the tools already being developed in cognitive science and AI research to accelerate progress towards concept alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08672 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Concept Alignment Rane, Sunayana Bruna, Polyphony J. Sucholutsky, Ilia Kello, Christopher Griffiths, Thomas L. Machine Learning Artificial Intelligence Neurons and Cognition Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is imperative that AI systems and humans align the concepts they use to understand the world. We integrate ideas from philosophy, cognitive science, and deep learning to explain the need for concept alignment, not just value alignment, between humans and machines. We summarize existing accounts of how humans and machines currently learn concepts, and we outline opportunities and challenges in the path towards shared concepts. Finally, we explain how we can leverage the tools already being developed in cognitive science and AI research to accelerate progress towards concept alignment. |
| title | Concept Alignment |
| topic | Machine Learning Artificial Intelligence Neurons and Cognition |
| url | https://arxiv.org/abs/2401.08672 |