Charting trajectories of human thought using large language models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911160856477696 |
|---|---|
| author | Nour, Matthew M McNamee, Daniel C Fradkin, Isaac Dolan, Raymond J |
| author_facet | Nour, Matthew M McNamee, Daniel C Fradkin, Isaac Dolan, Raymond J |
| contents | Language provides the most revealing window into the ways humans structure conceptual knowledge within cognitive maps. Harnessing this information has been difficult, given the challenge of reliably mapping words to mental concepts. Artificial Intelligence large language models (LLMs) now offer unprecedented opportunities to revisit this challenge. LLMs represent words and phrases as high-dimensional numerical vectors that encode vast semantic knowledge. To harness this potential for cognitive science, we introduce VECTOR, a computational framework that aligns LLM representations with human cognitive map organisation. VECTOR casts a participant's verbal reports as a geometric trajectory through a cognitive map representation, revealing how thoughts flow from one idea to the next. Applying VECTOR to narratives generated by 1,100 participants, we show these trajectories have cognitively meaningful properties that predict paralinguistic behaviour (response times) and real-world communication patterns. We suggest our approach opens new avenues for understanding how humans dynamically organise and navigate conceptual knowledge in naturalistic settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14455 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Charting trajectories of human thought using large language models Nour, Matthew M McNamee, Daniel C Fradkin, Isaac Dolan, Raymond J Neurons and Cognition Language provides the most revealing window into the ways humans structure conceptual knowledge within cognitive maps. Harnessing this information has been difficult, given the challenge of reliably mapping words to mental concepts. Artificial Intelligence large language models (LLMs) now offer unprecedented opportunities to revisit this challenge. LLMs represent words and phrases as high-dimensional numerical vectors that encode vast semantic knowledge. To harness this potential for cognitive science, we introduce VECTOR, a computational framework that aligns LLM representations with human cognitive map organisation. VECTOR casts a participant's verbal reports as a geometric trajectory through a cognitive map representation, revealing how thoughts flow from one idea to the next. Applying VECTOR to narratives generated by 1,100 participants, we show these trajectories have cognitively meaningful properties that predict paralinguistic behaviour (response times) and real-world communication patterns. We suggest our approach opens new avenues for understanding how humans dynamically organise and navigate conceptual knowledge in naturalistic settings. |
| title | Charting trajectories of human thought using large language models |
| topic | Neurons and Cognition |
| url | https://arxiv.org/abs/2509.14455 |