Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2410.00332 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915442628493312 |
|---|---|
| author | Luo, Dezhi Lyu, Haiyun Gao, Qingying Sun, Haoran Li, Yijiang Deng, Hokin |
| author_facet | Luo, Dezhi Lyu, Haiyun Gao, Qingying Sun, Haoran Li, Yijiang Deng, Hokin |
| contents | Understanding law of conservation is a critical milestone in human cognitive development considered to be supported by the apprehension of quantitative concepts and the reversibility of operations. To assess whether this critical component of human intelligence has emerged in Vision Language Models, we have curated the ConserveBench, a battery of 365 cognitive experiments across four dimensions of physical quantities: volume, solid quantity, length, and number. The former two involve transformational tasks which require reversibility understanding. The latter two involve non-transformational tasks which assess quantity understanding. Surprisingly, we find that while Vision Language Models are generally good at transformational tasks, they tend to fail at non-transformational tasks. There is a dissociation between understanding the reversibility of operations and understanding the concept of quantity, which both are believed to be the cornerstones of understanding law of conservation in humans. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_00332 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Vision Language Models Know Law of Conservation without Understanding More-or-Less Luo, Dezhi Lyu, Haiyun Gao, Qingying Sun, Haoran Li, Yijiang Deng, Hokin Artificial Intelligence Neurons and Cognition Understanding law of conservation is a critical milestone in human cognitive development considered to be supported by the apprehension of quantitative concepts and the reversibility of operations. To assess whether this critical component of human intelligence has emerged in Vision Language Models, we have curated the ConserveBench, a battery of 365 cognitive experiments across four dimensions of physical quantities: volume, solid quantity, length, and number. The former two involve transformational tasks which require reversibility understanding. The latter two involve non-transformational tasks which assess quantity understanding. Surprisingly, we find that while Vision Language Models are generally good at transformational tasks, they tend to fail at non-transformational tasks. There is a dissociation between understanding the reversibility of operations and understanding the concept of quantity, which both are believed to be the cornerstones of understanding law of conservation in humans. |
| title | Vision Language Models Know Law of Conservation without Understanding More-or-Less |
| topic | Artificial Intelligence Neurons and Cognition |
| url | https://arxiv.org/abs/2410.00332 |