Developmental trajectories of decision making and affective dynamics in 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_ | 1866915742275862528 |
|---|---|
| author | Wang, Zhihao Liu, Yiyang Wang, Ting Liu, Zhiyuan |
| author_facet | Wang, Zhihao Liu, Yiyang Wang, Ting Liu, Zhiyuan |
| contents | Large language models (LLMs) are increasingly used in medicine and clinical workflows, yet we know little about their decision and affective profiles. Taking a historically informed outlook on the future, we treated successive OpenAI models as an evolving lineage and compared them with humans in a gambling task with repeated happiness ratings. Computational analyses showed that some aspects became more human-like: newer models took more risks and displayed more human-like patterns of Pavlovian approach and avoidance. At the same time, distinctly non-human signatures emerged: loss aversion dropped below neutral levels, choices became more deterministic than in humans, affective decay increased across versions and exceeded human levels, and baseline mood remained chronically higher than in humans. These "developmental" trajectories reveal an emerging psychology of machines and have direct implications for AI ethics and for thinking about how LLMs might be integrated into clinical decision support and other high-stakes domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14268 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Developmental trajectories of decision making and affective dynamics in large language models Wang, Zhihao Liu, Yiyang Wang, Ting Liu, Zhiyuan Computers and Society Artificial Intelligence Computation and Language Large language models (LLMs) are increasingly used in medicine and clinical workflows, yet we know little about their decision and affective profiles. Taking a historically informed outlook on the future, we treated successive OpenAI models as an evolving lineage and compared them with humans in a gambling task with repeated happiness ratings. Computational analyses showed that some aspects became more human-like: newer models took more risks and displayed more human-like patterns of Pavlovian approach and avoidance. At the same time, distinctly non-human signatures emerged: loss aversion dropped below neutral levels, choices became more deterministic than in humans, affective decay increased across versions and exceeded human levels, and baseline mood remained chronically higher than in humans. These "developmental" trajectories reveal an emerging psychology of machines and have direct implications for AI ethics and for thinking about how LLMs might be integrated into clinical decision support and other high-stakes domains. |
| title | Developmental trajectories of decision making and affective dynamics in large language models |
| topic | Computers and Society Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2601.14268 |