Same Voice, Different Lab: On the Homogenization of Frontier LLM Personalities
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909013060354048 |
|---|---|
| author | Krishna, Avinash Chadalavada, Kalyana Jo, Unso Eun Seo |
| author_facet | Krishna, Avinash Chadalavada, Kalyana Jo, Unso Eun Seo |
| contents | LLM assistant personalities play a critical role in user experience and perceived response quality. We present a large-scale experiment of frontier LLM personalities using external ELO-based traits scoring across 144 traits. We find that all models tested converge on a form of trait expression that is systematic, methodical, and analytical and suppress traits such as remorseful and sycophantic. Moreover, models tend to diverge more in their expression of ``middle-of-distribution traits`` such as poetic or playful, but even these so-called ``creative`` models tend to have more neutral identities. These similarities suggest an implicit emergence of a standard of optimal assistant behavior. In a landscape of varied training methods, character training, therefore, stands out for its uniformity, offering insight into a tacit consensus between model developers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02897 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Same Voice, Different Lab: On the Homogenization of Frontier LLM Personalities Krishna, Avinash Chadalavada, Kalyana Jo, Unso Eun Seo Human-Computer Interaction Artificial Intelligence I.2.7 LLM assistant personalities play a critical role in user experience and perceived response quality. We present a large-scale experiment of frontier LLM personalities using external ELO-based traits scoring across 144 traits. We find that all models tested converge on a form of trait expression that is systematic, methodical, and analytical and suppress traits such as remorseful and sycophantic. Moreover, models tend to diverge more in their expression of ``middle-of-distribution traits`` such as poetic or playful, but even these so-called ``creative`` models tend to have more neutral identities. These similarities suggest an implicit emergence of a standard of optimal assistant behavior. In a landscape of varied training methods, character training, therefore, stands out for its uniformity, offering insight into a tacit consensus between model developers. |
| title | Same Voice, Different Lab: On the Homogenization of Frontier LLM Personalities |
| topic | Human-Computer Interaction Artificial Intelligence I.2.7 |
| url | https://arxiv.org/abs/2605.02897 |