Cultural Learning-Based Culture Adaptation of 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_ | 1866910902942433280 |
|---|---|
| author | Liu, Chen Cecilia Korhonen, Anna Gurevych, Iryna |
| author_facet | Liu, Chen Cecilia Korhonen, Anna Gurevych, Iryna |
| contents | Adapting large language models (LLMs) to diverse cultural values is a challenging task, as existing LLMs often reflect the values of specific groups by default, and potentially causing harm to others. In this paper, we present CLCA, a novel framework for enhancing LLM alignment with cultural values based on cultural learning. The framework leverages simulated social interactions to generate conversations in which LLMs engage in role-playing within culturally adapted social scenarios, capturing implicit cultural norms for model fine-tuning. CLCA improves cultural value alignment across various model architectures measured using World Value Survey data, demonstrating the effectiveness of our proposed approach. Our results provide early evidence that understanding intent and social interactions can enhance cultural value adaptation in LLMs, highlighting the promise of training approaches based on cultural learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02953 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cultural Learning-Based Culture Adaptation of Language Models Liu, Chen Cecilia Korhonen, Anna Gurevych, Iryna Computation and Language Adapting large language models (LLMs) to diverse cultural values is a challenging task, as existing LLMs often reflect the values of specific groups by default, and potentially causing harm to others. In this paper, we present CLCA, a novel framework for enhancing LLM alignment with cultural values based on cultural learning. The framework leverages simulated social interactions to generate conversations in which LLMs engage in role-playing within culturally adapted social scenarios, capturing implicit cultural norms for model fine-tuning. CLCA improves cultural value alignment across various model architectures measured using World Value Survey data, demonstrating the effectiveness of our proposed approach. Our results provide early evidence that understanding intent and social interactions can enhance cultural value adaptation in LLMs, highlighting the promise of training approaches based on cultural learning. |
| title | Cultural Learning-Based Culture Adaptation of Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.02953 |