Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2504.02789 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918219062706176 |
|---|---|
| author | de Langis, Karin Park, Jong Inn Hu, Bin Le, Khanh Chi Schramm, Andreas Mensink, Michael C. Elfenbein, Andrew Kang, Dongyeop |
| author_facet | de Langis, Karin Park, Jong Inn Hu, Bin Le, Khanh Chi Schramm, Andreas Mensink, Michael C. Elfenbein, Andrew Kang, Dongyeop |
| contents | Working memory, or the ability to hold and manipulate information in the mind, is a critical component of human intelligence and executive functioning. It is correlated with performance on various cognitive tasks, including measures of fluid intelligence, which encompasses reasoning and problem solving. We use a comprehensive set of classic working memory tasks to estimate the working memory capacity of large language models (LLMs). We find that in most cases, LLMs exceed normative human scores. However, we do not find that the increased capacity of working memory is associated with higher performance on other executive functioning tasks or problem solving benchmarks. These results suggest that LLMs may have deficits in attentional control and cognitive flexibility, which result in difficulties with inhibiting automatic responses and adapting to shifting information. Our findings suggest that current reasoning models have mixed results in compensating for these deficits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02789 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Strong Memory, Weak Control: An Empirical Study of Executive Functioning in LLMs de Langis, Karin Park, Jong Inn Hu, Bin Le, Khanh Chi Schramm, Andreas Mensink, Michael C. Elfenbein, Andrew Kang, Dongyeop Computation and Language Working memory, or the ability to hold and manipulate information in the mind, is a critical component of human intelligence and executive functioning. It is correlated with performance on various cognitive tasks, including measures of fluid intelligence, which encompasses reasoning and problem solving. We use a comprehensive set of classic working memory tasks to estimate the working memory capacity of large language models (LLMs). We find that in most cases, LLMs exceed normative human scores. However, we do not find that the increased capacity of working memory is associated with higher performance on other executive functioning tasks or problem solving benchmarks. These results suggest that LLMs may have deficits in attentional control and cognitive flexibility, which result in difficulties with inhibiting automatic responses and adapting to shifting information. Our findings suggest that current reasoning models have mixed results in compensating for these deficits. |
| title | Strong Memory, Weak Control: An Empirical Study of Executive Functioning in LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.02789 |