Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2604.16755 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913050515210240 |
|---|---|
| author | Kriegmair, Valentin Wulff, Dirk U. |
| author_facet | Kriegmair, Valentin Wulff, Dirk U. |
| contents | As large language models (LLMs) are increasingly integrated into daily life, in roles ranging from high-stakes decision support to companionship, understanding their behavioral dispositions becomes critical. A growing literature uses psychometric inventories and cognitive paradigms to profile LLM dispositions. However, these approaches cannot determine whether behavioral differences reflect stable, stimulus-specific individuality or global response biases and stochastic noise. Here, we apply crossed random-effects models -- widely used in psychometrics to separate systematic effects -- to 74.9 million ratings provided by 10 open-weight LLMs for over 100,000 words across 14 psycholinguistic norms. On average, 16.9% of variance is attributable to stimulus-specific individuality, robustly exceeding a statistical null model. Cross-norm prediction analyses reveal this individuality as a coherent fingerprint, unique to each model. These results identify individual differences among LLMs that cannot be attributed to response biases or stochastic noise. We term these differences machine individuality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16755 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Machine individuality: Separating genuine idiosyncrasy from response bias in large language models Kriegmair, Valentin Wulff, Dirk U. Artificial Intelligence As large language models (LLMs) are increasingly integrated into daily life, in roles ranging from high-stakes decision support to companionship, understanding their behavioral dispositions becomes critical. A growing literature uses psychometric inventories and cognitive paradigms to profile LLM dispositions. However, these approaches cannot determine whether behavioral differences reflect stable, stimulus-specific individuality or global response biases and stochastic noise. Here, we apply crossed random-effects models -- widely used in psychometrics to separate systematic effects -- to 74.9 million ratings provided by 10 open-weight LLMs for over 100,000 words across 14 psycholinguistic norms. On average, 16.9% of variance is attributable to stimulus-specific individuality, robustly exceeding a statistical null model. Cross-norm prediction analyses reveal this individuality as a coherent fingerprint, unique to each model. These results identify individual differences among LLMs that cannot be attributed to response biases or stochastic noise. We term these differences machine individuality. |
| title | Machine individuality: Separating genuine idiosyncrasy from response bias in large language models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.16755 |