Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.15626 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913860356669440 |
|---|---|
| author | Ilievski, Filip Hammer, Barbara van Harmelen, Frank Paassen, Benjamin Saralajew, Sascha Schmid, Ute Biehl, Michael Bolognesi, Marianna Dong, Xin Luna Gashteovski, Kiril Hitzler, Pascal Marra, Giuseppe Minervini, Pasquale Mundt, Martin Ngomo, Axel-Cyrille Ngonga Oltramari, Alessandro Pasi, Gabriella Saribatur, Zeynep G. Serafini, Luciano Shawe-Taylor, John Shwartz, Vered Skitalinskaya, Gabriella Stachl, Clemens van de Ven, Gido M. Villmann, Thomas |
| author_facet | Ilievski, Filip Hammer, Barbara van Harmelen, Frank Paassen, Benjamin Saralajew, Sascha Schmid, Ute Biehl, Michael Bolognesi, Marianna Dong, Xin Luna Gashteovski, Kiril Hitzler, Pascal Marra, Giuseppe Minervini, Pasquale Mundt, Martin Ngomo, Axel-Cyrille Ngonga Oltramari, Alessandro Pasi, Gabriella Saribatur, Zeynep G. Serafini, Luciano Shawe-Taylor, John Shwartz, Vered Skitalinskaya, Gabriella Stachl, Clemens van de Ven, Gido M. Villmann, Thomas |
| contents | Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and forming decisions, but may also disrupt democracies and target individuals. The responsible use of AI and its participation in human-AI teams increasingly shows the need for AI alignment, that is, to make AI systems act according to our preferences. A crucial yet often overlooked aspect of these interactions is the different ways in which humans and machines generalise. In cognitive science, human generalisation commonly involves abstraction and concept learning. In contrast, AI generalisation encompasses out-of-domain generalisation in machine learning, rule-based reasoning in symbolic AI, and abstraction in neurosymbolic AI. In this perspective paper, we combine insights from AI and cognitive science to identify key commonalities and differences across three dimensions: notions of, methods for, and evaluation of generalisation. We map the different conceptualisations of generalisation in AI and cognitive science along these three dimensions and consider their role for alignment in human-AI teaming. This results in interdisciplinary challenges across AI and cognitive science that must be tackled to provide a foundation for effective and cognitively supported alignment in human-AI teaming scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15626 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Aligning Generalisation Between Humans and Machines Ilievski, Filip Hammer, Barbara van Harmelen, Frank Paassen, Benjamin Saralajew, Sascha Schmid, Ute Biehl, Michael Bolognesi, Marianna Dong, Xin Luna Gashteovski, Kiril Hitzler, Pascal Marra, Giuseppe Minervini, Pasquale Mundt, Martin Ngomo, Axel-Cyrille Ngonga Oltramari, Alessandro Pasi, Gabriella Saribatur, Zeynep G. Serafini, Luciano Shawe-Taylor, John Shwartz, Vered Skitalinskaya, Gabriella Stachl, Clemens van de Ven, Gido M. Villmann, Thomas Artificial Intelligence Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and forming decisions, but may also disrupt democracies and target individuals. The responsible use of AI and its participation in human-AI teams increasingly shows the need for AI alignment, that is, to make AI systems act according to our preferences. A crucial yet often overlooked aspect of these interactions is the different ways in which humans and machines generalise. In cognitive science, human generalisation commonly involves abstraction and concept learning. In contrast, AI generalisation encompasses out-of-domain generalisation in machine learning, rule-based reasoning in symbolic AI, and abstraction in neurosymbolic AI. In this perspective paper, we combine insights from AI and cognitive science to identify key commonalities and differences across three dimensions: notions of, methods for, and evaluation of generalisation. We map the different conceptualisations of generalisation in AI and cognitive science along these three dimensions and consider their role for alignment in human-AI teaming. This results in interdisciplinary challenges across AI and cognitive science that must be tackled to provide a foundation for effective and cognitively supported alignment in human-AI teaming scenarios. |
| title | Aligning Generalisation Between Humans and Machines |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2411.15626 |