Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
This addresses the issue of culturally sensitive decision-making for users of LLMs, representing an incremental improvement through a novel method for a known bottleneck.
The paper tackles the problem of cultural misalignment in LLMs by proposing OG-MAR, an ontology-guided multi-agent reasoning framework that improves cultural alignment and robustness on regional social-survey benchmarks across four LLM backbones.
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.