Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI

• URL: http://arxiv.org/abs/2508.05432v1
• Date: Thu, 07 Aug 2025 14:21:33 GMT
• Title: Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI
• Abstract summary: What is considered appropriate, truthful, or legal can differ widely across regions due to cultural norms, political realities, and legislation.<n>This paper reviews key geographic research problems, suggests topics for future work, and outlines methods for assessing alignment sensitivity.
• Score: 42.108524228070756
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI (super) alignment describes the challenge of ensuring (future) AI systems behave in accordance with societal norms and goals. While a quickly evolving literature is addressing biases and inequalities, the geographic variability of alignment remains underexplored. Simply put, what is considered appropriate, truthful, or legal can differ widely across regions due to cultural norms, political realities, and legislation. Alignment measures applied to AI/ML workflows can sometimes produce outcomes that diverge from statistical realities, such as text-to-image models depicting balanced gender ratios in company leadership despite existing imbalances. Crucially, some model outputs are globally acceptable, while others, e.g., questions about Kashmir, depend on knowing the user's location and their context. This geographic sensitivity is not new. For instance, Google Maps renders Kashmir's borders differently based on user location. What is new is the unprecedented scale and automation with which AI now mediates knowledge, expresses opinions, and represents geographic reality to millions of users worldwide, often with little transparency about how context is managed. As we approach Agentic AI, the need for spatio-temporally aware alignment, rather than one-size-fits-all approaches, is increasingly urgent. This paper reviews key geographic research problems, suggests topics for future work, and outlines methods for assessing alignment sensitivity.

Related papers

• Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups [1.9307952728103126]
  Large Language Models (LLMs) are increasingly shaping how we consume information and form our worldview.<n>This raises concerns beyond bias in AI: do LLMs grasp the emotional nuances conveyed via textual framing?<n>We empirically evaluate how well an array of LLMs aligns with human emotional perception.
  arXiv  Detail & Related papers  (2026-07-22T16:23:26Z)
• 'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic Assumptions [50.1119556361129]
  We systematically define various notions of AI-generated text and their characteristics.<n>AITDNA is a new benchmark of human-machine co-constructed texts.<n>We benchmark various machine-generated text detectors and find that they often only perform well for specific notions but not as broad detectors.
  arXiv  Detail & Related papers  (2026-06-03T14:05:14Z)
• Geographic Bias and Diversity in AI Evaluation [13.861735837455626]
  This chapter investigates the geographical nature of bias in (generative) AI.<n>We identify a range of geographic biases that span from representation bias in the training data to regional disparities in the factual recall of language models.<n>We showcase how recent studies address the latter bias by evaluating geographic diversity in the outputs of generative AI.
  arXiv  Detail & Related papers  (2026-04-28T11:32:32Z)
• Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond [209.35045331678043]
  We introduce a "levels x laws" taxonomy organized along two axes.<n>The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence.<n>We synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery.
  arXiv  Detail & Related papers  (2026-04-24T17:48:47Z)
• OBSR: Open Benchmark for Spatial Representations [0.3936827689390718]
  This paper introduces a novel benchmark designed to assess the performance, accuracy, and efficiency of geospatial embedders.<n>Our benchmark is modality-agnostic and comprises 7 distinct datasets from diverse cities across three continents.
  arXiv  Detail & Related papers  (2025-10-07T12:48:48Z)
• Street-Level AI: Are Large Language Models Ready for Real-World Judgments? [10.76443470676701]
  Most immediate and likely use of AI is to help or fully replace the so-called street-level bureaucrats.<n>In this paper, we examine how well LLM judgments align with human judgments.<n>We find that LLM prioritizations are extremely inconsistent in several ways.
  arXiv  Detail & Related papers  (2025-08-11T17:12:55Z)
• Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models [52.00270888041742]
  We introduce a novel dataset with neutral event descriptions and contrasting viewpoints from different countries.<n>Our findings show significant geopolitical biases, with models favoring specific national narratives.<n>Simple debiasing prompts had a limited effect on reducing these biases.
  arXiv  Detail & Related papers  (2025-06-07T10:45:17Z)
• The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm [17.566947609534356]
  AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. We collect the first set of human annotated red-teaming prompts in different languages distinguishing between global and local harm. We establish a new precedent for state-of-the-art alignment techniques across 6 languages with minimal degradation in general performance.
  arXiv  Detail & Related papers  (2024-06-26T18:39:08Z)
• Quantifying Misalignment Between Agents: Towards a Sociotechnical Understanding of Alignment [2.619545850602691]
  Recent sociotechnical approaches highlight the need to understand complex misalignment among multiple human and AI agents.<n>We adapt a computational social science model of human contention to the alignment problem.<n>Our model quantifies misalignment in large, diverse agent groups with potentially conflicting goals.
  arXiv  Detail & Related papers  (2024-06-06T16:31:22Z)
• Large Language Models are Geographically Biased [47.88767211956144]
  We study what Large Language Models (LLMs) know about the world we live in through the lens of geography. We show various problematic geographic biases, which we define as systemic errors in geospatial predictions.
  arXiv  Detail & Related papers  (2024-02-05T02:32:09Z)
• AI Alignment: A Comprehensive Survey [69.61425542486275]
  AI alignment aims to make AI systems behave in line with human intentions and values.<n>We identify four principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality.<n>We decompose current alignment research into two key components: forward alignment and backward alignment.
  arXiv  Detail & Related papers  (2023-10-30T15:52:15Z)
• GeoNet: Benchmarking Unsupervised Adaptation across Geographies [71.23141626803287]
  We study the problem of geographic robustness and make three main contributions. First, we introduce a large-scale dataset GeoNet for geographic adaptation. Second, we hypothesize that the major source of domain shifts arise from significant variations in scene context. Third, we conduct an extensive evaluation of several state-of-the-art unsupervised domain adaptation algorithms and architectures.
  arXiv  Detail & Related papers  (2023-03-27T17:59:34Z)
• Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics [80.07271410743806]
  We study the relationship between cross-domain learning (CD) and model fairness. We introduce a benchmark on face and medical images spanning several demographic groups as well as classification and localization tasks. Our study covers 14 CD approaches alongside three state-of-the-art fairness algorithms and shows how the former can outperform the latter.
  arXiv  Detail & Related papers  (2023-03-25T09:34:05Z)
• Bias, diversity, and challenges to fairness in classification and automated text analysis. From libraries to AI and back [3.9198548406564604]
  We investigate the risks surrounding bias and unfairness in AI usage in classification and automated text analysis. We take a closer look at the notion of '(un)fairness' in relation to the notion of 'diversity'
  arXiv  Detail & Related papers  (2023-03-07T20:54:49Z)
• LioNets: A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information [6.570220157893279]
  Interpretable machine learning (IML) is an urgent topic of research. This paper focuses on a local-based, neural-specific interpretation process applied to textual and time-series data.
  arXiv  Detail & Related papers  (2021-04-13T09:39:33Z)
• Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association [94.7030305679589]
  We propose a novel framework to jointly address the above-mentioned issues. We introduce a global loss into the modality alignment process. The proposed method outperforms the previous methods in multiple settings.
  arXiv  Detail & Related papers  (2021-03-12T14:10:48Z)
• A New Bandit Setting Balancing Information from State Evolution and Corrupted Context [52.67844649650687]
  We propose a new sequential decision-making setting combining key aspects of two established online learning problems with bandit feedback. The optimal action to play at any given moment is contingent on an underlying changing state which is not directly observable by the agent. We present an algorithm that uses a referee to dynamically combine the policies of a contextual bandit and a multi-armed bandit.
  arXiv  Detail & Related papers  (2020-11-16T14:35:37Z)
• Data, Power and Bias in Artificial Intelligence [5.124256074746721]
  Artificial Intelligence has the potential to exacerbate societal bias and set back decades of advances in equal rights and civil liberty. Data used to train machine learning algorithms may capture social injustices, inequality or discriminatory attitudes that may be learned and perpetuated in society. This paper reviews ongoing work to ensure data justice, fairness and bias mitigation in AI systems from different domains.
  arXiv  Detail & Related papers  (2020-07-28T16:17:40Z)

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.