The Geopolitics of AI Safety: A Causal Analysis of Regional LLM Bias

• URL: http://arxiv.org/abs/2605.05427v1
• Date: Wed, 06 May 2026 20:35:57 GMT
• Title: The Geopolitics of AI Safety: A Causal Analysis of Regional LLM Bias
• Abstract summary: This study introduces a Probabilistic Graphical Model (PGM) framework to audit Large Language Models causally.<n>We conduct a large-scale empirical analysis across seven instruction-tuned models spanning diverse origins.<n>We discuss the implications of these biases, highlighting how demographic-sensitive over-triggering restricts benign discourse in downstream applications.
• Score: 0.20305676256390937
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Large Language Models (LLMs) are integrated into global software systems, ensuring equitable safety guardrails is a critical requirement. Current fairness evaluations predominantly measure bias observationally, a methodology confounded by the inherent toxicity of topics naturally paired with specific demographics in testing datasets. This study introduces a Probabilistic Graphical Model (PGM) framework to audit LLM safety mechanisms causally. By applying Pearl's do-operator, we mathematically isolate the causal effect of injecting a cultural demographic into a prompt. We conduct a large-scale empirical analysis across seven instruction-tuned models spanning diverse origins: the United States (Llama-3.1-8B, Gemma-2-9B), Europe (Mistral-7B-v0.3), the UAE (Falcon3-7B), China (Qwen2.5-7B, DeepSeek-7B), and India (Airavata-7B). Utilizing two distinct datasets (ToxiGen and BOLD), the findings reveal a disparity between observational and interventional bias, demonstrating that standard fairness metrics can overestimate demographic bias by failing to account for context toxicity. Furthermore, the causal probabilities indicate distinct alignment trends: Western models exhibit higher causal refusal rates for specific demographic groups, whereas Eastern models demonstrate low overall intervention rates with targeted sensitivities toward regional demographics. We discuss the implications of these biases, highlighting how demographic-sensitive over-triggering restricts benign discourse in downstream applications.

Related papers

• Auditing demographic bias in AI-based emergency police dispatch: a cross-lingual evaluation of eleven large language models [3.85700834433791]
  We introduce a cross-lingual audit framework to operationalize the Police Priority Dispatch System.<n>We find that demographic bias emerges systematically when incident severity is ambiguous.<n>Gender bias is substantially amplified in Mandarin Chinese, whereas race bias is more pronounced in English.
  arXiv  Detail & Related papers  (2026-05-02T14:00:57Z)
• Sociodemographic Biases in Educational Counselling by Large Language Models [61.30199414932204]
  This study examines sociodemographic biases in Large Language Models (LLMs)<n>We evaluate responses from six LLMs answering questions about 900 vignettes describing students in diverse circumstances.
  arXiv  Detail & Related papers  (2026-04-03T14:08:22Z)
• Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study [1.6682715542079583]
  Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases.<n>We present a comprehensive evaluation framework aimed at English texts to assess the ability of LLMs in detecting demographic-targeted social biases.<n>We then conduct a systematic evaluation with models across scales and techniques, including prompting, in-context learning, and fine-tuning.
  arXiv  Detail & Related papers  (2025-10-06T09:45:32Z)
• DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models [5.024921806058944]
  Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities across various downstream tasks, including biometric face recognition (FR) with description.<n>We conduct an empirical evaluation to investigate the extent of demographic biases in LVLMs for biometric FR with textual token generation tasks.
  arXiv  Detail & Related papers  (2025-08-25T18:02:49Z)
• Who's Asking? Investigating Bias Through the Lens of Disability Framed Queries in LLMs [2.722784054643991]
  Large Language Models (LLMs) routinely infer users demographic traits from phrasing alone.<n>Disability cues in shaping these inferences remains largely uncharted.<n>We present the first systematic audit of disability-conditioned demographic bias across eight state-of-the-art instruction-tuned LLMs.
  arXiv  Detail & Related papers  (2025-08-18T21:03:09Z)
• Fair Deepfake Detectors Can Generalize [51.21167546843708]
  We show that controlling for confounders (data distribution and model capacity) enables improved generalization via fairness interventions.<n>Motivated by this insight, we propose Demographic Attribute-insensitive Intervention Detection (DAID), a plug-and-play framework composed of: i) Demographic-aware data rebalancing, which employs inverse-propensity weighting and subgroup-wise feature normalization to neutralize distributional biases; and ii) Demographic-agnostic feature aggregation, which uses a novel alignment loss to suppress sensitive-attribute signals.<n>DAID consistently achieves superior performance in both fairness and generalization compared to several state-of-the-art
  arXiv  Detail & Related papers  (2025-07-03T14:10:02Z)
• A Feature-level Bias Evaluation Framework for Facial Expression Recognition Models [0.0]
  We introduce a plug-and-play statistical module to ensure the statistical significance of biased evaluation results.<n>A comprehensive bias analysis is then conducted across three sensitive attributes (age, gender, and race), seven facial expressions, and multiple network architectures on a large-scale dataset.
  arXiv  Detail & Related papers  (2025-05-26T20:26:07Z)
• Identifying and Mitigating Social Bias Knowledge in Language Models [52.52955281662332]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.<n>FAST surpasses state-of-the-art baselines with superior debiasing performance.<n>This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective [66.34066553400108]
  We conduct a rigorous evaluation of large language models' implicit bias towards certain demographics.<n>Inspired by psychometric principles, we propose three attack approaches, i.e., Disguise, Deception, and Teaching.<n>Our methods can elicit LLMs' inner bias more effectively than competitive baselines.
  arXiv  Detail & Related papers  (2024-06-20T06:42:08Z)
• Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
  We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy. We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
  arXiv  Detail & Related papers  (2023-02-22T14:50:24Z)
• Towards Controllable Biases in Language Generation [87.89632038677912]
  We develop a method to induce societal biases in generated text when input prompts contain mentions of specific demographic groups. We analyze two scenarios: 1) inducing negative biases for one demographic and positive biases for another demographic, and 2) equalizing biases between demographics.
  arXiv  Detail & Related papers  (2020-05-01T08:25:11Z)

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.