Reply to "Emergent LLM behaviors are observationally equivalent to data leakage"
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909656945786880 |
|---|---|
| author | Ashery, Ariel Flint Aiello, Luca Maria Baronchelli, Andrea |
| author_facet | Ashery, Ariel Flint Aiello, Luca Maria Baronchelli, Andrea |
| contents | A potential concern when simulating populations of large language models (LLMs) is data contamination, i.e. the possibility that training data may shape outcomes in unintended ways. While this concern is important and may hinder certain experiments with multi-agent models, it does not preclude the study of genuinely emergent dynamics in LLM populations. The recent critique by Barrie and Törnberg [1] of the results of Flint Ashery et al. [2] offers an opportunity to clarify that self-organisation and model-dependent emergent dynamics can be studied in LLM populations, highlighting how such dynamics have been empirically observed in the specific case of social conventions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18600 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reply to "Emergent LLM behaviors are observationally equivalent to data leakage" Ashery, Ariel Flint Aiello, Luca Maria Baronchelli, Andrea Computation and Language Computer Science and Game Theory Multiagent Systems A potential concern when simulating populations of large language models (LLMs) is data contamination, i.e. the possibility that training data may shape outcomes in unintended ways. While this concern is important and may hinder certain experiments with multi-agent models, it does not preclude the study of genuinely emergent dynamics in LLM populations. The recent critique by Barrie and Törnberg [1] of the results of Flint Ashery et al. [2] offers an opportunity to clarify that self-organisation and model-dependent emergent dynamics can be studied in LLM populations, highlighting how such dynamics have been empirically observed in the specific case of social conventions. |
| title | Reply to "Emergent LLM behaviors are observationally equivalent to data leakage" |
| topic | Computation and Language Computer Science and Game Theory Multiagent Systems |
| url | https://arxiv.org/abs/2506.18600 |