Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning

• URL: http://arxiv.org/abs/2601.21700v2
• Date: Fri, 30 Jan 2026 03:28:25 GMT
• Title: Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
• Authors: Wonduk Seo, Wonseok Choi, Junseo Koh, Juhyeon Lee, Hyunjin An, Minhyeong Yu, Jian Park, Qingshan Zhou, Seunghyun Lee, Yi Bu,
• Abstract summary: We propose OG-MAR, an Ontology-Guided Multi-Agent Reasoning framework.<n> OG-MAR summarizes respondent-specific values from the World Values Survey (WVS).<n>It constructs a global cultural ontology by eliciting relations over a fixed taxonomy via competency questions.<n>At inference time, it retrieves demographically similar profiles to instantiate multiple value-persona agents.
• Score: 6.102462703832761
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations [63.478832978278014]
  Large language models (LLMs) are increasingly deployed as autonomous agents, yet evaluations focus primarily on task success rather than cultural appropriateness or evaluator reliability.<n>We introduce LiveCultureBench, a multi-cultural, dynamic benchmark that embeds LLMs as agents in a simulated town and evaluates them on both task completion and adherence to socio-cultural norms.
  arXiv  Detail & Related papers  (2026-03-02T15:04:16Z)
• Multimodal Fact-Level Attribution for Verifiable Reasoning [80.60864342985748]
  Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation.<n>Existing multimodal grounding benchmarks and evaluation methods fail to assess attribution in complex multimodal reasoning.<n>We introduce MuRGAt, a benchmark for evaluating fact-level multimodal attribution in settings that require reasoning beyond direct observation.
  arXiv  Detail & Related papers  (2026-02-12T03:10:02Z)
• Beyond Marginal Distributions: A Framework to Evaluate the Representativeness of Demographic-Aligned LLMs [13.630995219491972]
  We propose a framework for evaluating the representativeness of aligned models.<n>We show the value of our evaluation scheme by comparing two model steering techniques.<n>We conclude that representativeness is a distinct aspect of value alignment.
  arXiv  Detail & Related papers  (2026-01-22T08:45:55Z)
• Cross-cultural value alignment frameworks for responsible AI governance: Evidence from China-West comparative analysis [20.31675378963816]
  This study systematically evaluates cross-cultural value alignment in China-origin and Western-origin Large Language Models (LLMs)<n>Our comparative analysis of leading models, such as Qwen, GPT-4o, Claude, LLaMA, and DeepSeek, reveals universal challenges-fundamental instability in value systems, systematic under-representation of younger demographics, and non-linear relationships between model scale and alignment quality-alongside divergent regional development trajectories.
  arXiv  Detail & Related papers  (2025-11-21T14:02:33Z)
• I Am Aligned, But With Whom? MENA Values Benchmark for Evaluating Cultural Alignment and Multilingual Bias in LLMs [5.060243371992739]
  We introduce MENAValues, a novel benchmark designed to evaluate the cultural alignment and multilingual biases of large language models (LLMs)<n> Drawing from large-scale, authoritative human surveys, we curate a structured dataset that captures the sociocultural landscape of MENA with population-level response distributions from 16 countries.<n>Our analysis reveals three critical phenomena: "Cross-Lingual Value Shifts" where identical questions yield drastically different responses based on language, "Reasoning-Induced Degradation" where prompting models to explain their reasoning worsens cultural alignment, and "Logit Leakage" where models refuse sensitive questions while internal probabilities reveal strong hidden
  arXiv  Detail & Related papers  (2025-10-15T05:10:57Z)
• MoVa: Towards Generalizable Classification of Human Morals and Values [57.93595662296688]
  MoVa is a well-documented suite of resources for generalizable classification of human morals and values.<n>The data and methods in MoVa can facilitate many fine-grained interpretations of human and machine communication.
  arXiv  Detail & Related papers  (2025-09-29T02:56:27Z)
• Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced Contexts [10.492471013369782]
  We present a framework that treats sentiment as a context-dependent, culturally embedded construct.<n>We evaluate how large language models (LLMs) reason about sentiment in WhatsApp messages from Nairobi youth health groups.
  arXiv  Detail & Related papers  (2025-08-06T08:27:55Z)
• Do Large Language Models Understand Morality Across Cultures? [0.5356944479760104]
  This study investigates the extent to which large language models capture cross-cultural differences and similarities in moral perspectives.<n>Our results reveal that current LLMs often fail to reproduce the full spectrum of cross-cultural moral variation.<n>These findings highlight a pressing need for more robust approaches to mitigate biases and improve cultural representativeness in LLMs.
  arXiv  Detail & Related papers  (2025-07-28T20:25:36Z)
• Hallucination Detection in LLMs with Topological Divergence on Attention Graphs [60.83579255387347]
  Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models.<n>We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting.
  arXiv  Detail & Related papers  (2025-04-14T10:06:27Z)
• A Survey on Post-training of Large Language Models [185.51013463503946]
  Large Language Models (LLMs) have fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration.<n>These challenges necessitate advanced post-training language models (PoLMs) to address shortcomings, such as restricted reasoning capacities, ethical uncertainties, and suboptimal domain-specific performance.<n>This paper presents the first comprehensive survey of PoLMs, systematically tracing their evolution across five core paradigms: Fine-tuning, which enhances task-specific accuracy; Alignment, which ensures ethical coherence and alignment with human preferences; Reasoning, which advances multi-step inference despite challenges in reward design; Integration and Adaptation, which
  arXiv  Detail & Related papers  (2025-03-08T05:41:42Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.