Are the LLMs Capable of Maintaining at Least the Language Genus?
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908610265612288 |
|---|---|
| author | Mitrović, Sandra Kletz, David Dolamic, Ljiljana Rinaldi, Fabio |
| author_facet | Mitrović, Sandra Kletz, David Dolamic, Ljiljana Rinaldi, Fabio |
| contents | Large Language Models (LLMs) display notable variation in multilingual behavior, yet the role of genealogical language structure in shaping this variation remains underexplored. In this paper, we investigate whether LLMs exhibit sensitivity to linguistic genera by extending prior analyses on the MultiQ dataset. We first check if models prefer to switch to genealogically related languages when prompt language fidelity is not maintained. Next, we investigate whether knowledge consistency is better preserved within than across genera. We show that genus-level effects are present but strongly conditioned by training resource availability. We further observe distinct multilingual strategies across LLMs families. Our findings suggest that LLMs encode aspects of genus-level structure, but training data imbalances remain the primary factor shaping their multilingual performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21561 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Are the LLMs Capable of Maintaining at Least the Language Genus? Mitrović, Sandra Kletz, David Dolamic, Ljiljana Rinaldi, Fabio Computation and Language Large Language Models (LLMs) display notable variation in multilingual behavior, yet the role of genealogical language structure in shaping this variation remains underexplored. In this paper, we investigate whether LLMs exhibit sensitivity to linguistic genera by extending prior analyses on the MultiQ dataset. We first check if models prefer to switch to genealogically related languages when prompt language fidelity is not maintained. Next, we investigate whether knowledge consistency is better preserved within than across genera. We show that genus-level effects are present but strongly conditioned by training resource availability. We further observe distinct multilingual strategies across LLMs families. Our findings suggest that LLMs encode aspects of genus-level structure, but training data imbalances remain the primary factor shaping their multilingual performance. |
| title | Are the LLMs Capable of Maintaining at Least the Language Genus? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.21561 |