Emergence of psychopathological computations in large language models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917096727773184 |
|---|---|
| author | Lee, Soo Yong Hwang, Hyunjin Kim, Taekwan Kim, Yuyeong Park, Kyuri Yoo, Jaemin Borsboom, Denny Shin, Kijung |
| author_facet | Lee, Soo Yong Hwang, Hyunjin Kim, Taekwan Kim, Yuyeong Park, Kyuri Yoo, Jaemin Borsboom, Denny Shin, Kijung |
| contents | Can large language models (LLMs) instantiate computations of psychopathology? An effective approach to the question hinges on addressing two factors. First, for conceptual validity, we require a general and computational account of psychopathology that is applicable to computational entities without biological embodiment or subjective experience. Second, psychopathological computations, derived from the adapted theory, need to be empirically identified within the LLM's internal processing. Thus, we establish a computational-theoretical framework to provide an account of psychopathology applicable to LLMs. Based on the framework, we conduct experiments demonstrating two key claims: first, that the computational structure of psychopathology exists in LLMs; and second, that executing this computational structure results in psychopathological functions. We further observe that as LLM size increases, the computational structure of psychopathology becomes denser and that the functions become more effective. Taken together, the empirical results corroborate our hypothesis that network-theoretic computations of psychopathology have already emerged in LLMs. This suggests that certain LLM behaviors mirroring psychopathology may not be a superficial mimicry but a feature of their internal processing. Our work shows the promise of developing a new powerful in silico model of psychopathology and also alludes to the possibility of safety threat from the AI systems with psychopathological behaviors in the near future. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_08016 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Emergence of psychopathological computations in large language models Lee, Soo Yong Hwang, Hyunjin Kim, Taekwan Kim, Yuyeong Park, Kyuri Yoo, Jaemin Borsboom, Denny Shin, Kijung Neurons and Cognition Artificial Intelligence Computation and Language Can large language models (LLMs) instantiate computations of psychopathology? An effective approach to the question hinges on addressing two factors. First, for conceptual validity, we require a general and computational account of psychopathology that is applicable to computational entities without biological embodiment or subjective experience. Second, psychopathological computations, derived from the adapted theory, need to be empirically identified within the LLM's internal processing. Thus, we establish a computational-theoretical framework to provide an account of psychopathology applicable to LLMs. Based on the framework, we conduct experiments demonstrating two key claims: first, that the computational structure of psychopathology exists in LLMs; and second, that executing this computational structure results in psychopathological functions. We further observe that as LLM size increases, the computational structure of psychopathology becomes denser and that the functions become more effective. Taken together, the empirical results corroborate our hypothesis that network-theoretic computations of psychopathology have already emerged in LLMs. This suggests that certain LLM behaviors mirroring psychopathology may not be a superficial mimicry but a feature of their internal processing. Our work shows the promise of developing a new powerful in silico model of psychopathology and also alludes to the possibility of safety threat from the AI systems with psychopathological behaviors in the near future. |
| title | Emergence of psychopathological computations in large language models |
| topic | Neurons and Cognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2504.08016 |