Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918314180083712 |
|---|---|
| author | Seo, Wonduk Choi, Wonseok Koh, Junseo Lee, Juhyeon An, Hyunjin Yu, Minhyeong Park, Jian Zhou, Qingshan Lee, Seunghyun Bu, Yi |
| author_facet | Seo, Wonduk Choi, Wonseok Koh, Junseo Lee, Juhyeon An, Hyunjin Yu, Minhyeong Park, Jian Zhou, Qingshan Lee, Seunghyun Bu, Yi |
| contents | Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured value representations. Existing methods can steer outputs, but often lack demographic grounding and treat values as independent, unstructured signals, reducing consistency and interpretability. We propose OG-MAR, an Ontology-Guided Multi-Agent Reasoning framework. OG-MAR summarizes respondent-specific values from the World Values Survey (WVS) and constructs a global cultural ontology by eliciting relations over a fixed taxonomy via competency questions. At inference time, it retrieves ontology-consistent relations and demographically similar profiles to instantiate multiple value-persona agents, whose outputs are synthesized by a judgment agent that enforces ontology consistency and demographic proximity. Experiments on regional social-survey benchmarks across four LLM backbones show that OG-MAR improves cultural alignment and robustness over competitive baselines, while producing more transparent reasoning traces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21700 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning Seo, Wonduk Choi, Wonseok Koh, Junseo Lee, Juhyeon An, Hyunjin Yu, Minhyeong Park, Jian Zhou, Qingshan Lee, Seunghyun Bu, Yi Computation and Language Artificial Intelligence Information Retrieval Multiagent Systems Social and Information Networks Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured value representations. Existing methods can steer outputs, but often lack demographic grounding and treat values as independent, unstructured signals, reducing consistency and interpretability. We propose OG-MAR, an Ontology-Guided Multi-Agent Reasoning framework. OG-MAR summarizes respondent-specific values from the World Values Survey (WVS) and constructs a global cultural ontology by eliciting relations over a fixed taxonomy via competency questions. At inference time, it retrieves ontology-consistent relations and demographically similar profiles to instantiate multiple value-persona agents, whose outputs are synthesized by a judgment agent that enforces ontology consistency and demographic proximity. Experiments on regional social-survey benchmarks across four LLM backbones show that OG-MAR improves cultural alignment and robustness over competitive baselines, while producing more transparent reasoning traces. |
| title | Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning |
| topic | Computation and Language Artificial Intelligence Information Retrieval Multiagent Systems Social and Information Networks |
| url | https://arxiv.org/abs/2601.21700 |