Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version

• URL: http://arxiv.org/abs/2606.11399v1
• Date: Tue, 09 Jun 2026 19:44:23 GMT
• Title: Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version
• Abstract summary: We propose a framework for probing and steering latent cultural representations in large language models.<n>By translating social value questions into scenario-based behavioral dilemmas, we extract token-level probabilities to measure implicit values.<n>We find substantial variation in steerability and identify latent entanglement, where interventions along one cultural dimension shifts along another.
• Score: 5.97627108250811
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large Language Models (LLMs) are deployed across cultural contexts but often reflect homogenized values inherited from training data. Evaluations of cultural alignment typically rely on direct prompting with survey-style questions, which frequently elicit neutral or safety-aligned responses and fail to capture underlying model preferences. We propose a framework for probing and steering latent cultural representations in LLMs along the two Inglehart--Welzel axes of the World Values Survey (WVS). By translating social value questions into scenario-based behavioral dilemmas, we extract token-level probabilities to measure implicit values and apply activation steering, optionally combined with country-conditioned prompting, to shift model behavior without retraining. Across three open-source LLMs and four target cultures, we find substantial variation in steerability and identify latent entanglement, where interventions along one cultural dimension induce shifts along another. This coupling mirrors correlations in human WVS data and persists across activation, prompt, and hybrid steering. It constrains axis-independent alignment, though general task performance is largely preserved.

Related papers

• Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs [51.56484100374058]
  Large Language Models (LLMs) demonstrate remarkable multilingual fluency, but their internal knowledge representations remain disproportionately biased toward high-resource languages.<n>We investigate whether these biases can be mitigated at inference time, forcing an English-prompted model to answer as if it were queried in target languages.<n>Experiments on Gemma 3 12B Instruct reveal persona prompting to be the strongest overall intervention, balancing efficacy, safety, and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-07-21T16:15:05Z)
• Cultural Value Alignment Via Latent Activation Steering in Large Language Models [4.181458436156503]
  We propose a generalizable framework for cultural evaluation and intervention.<n>By extracting implicit token probabilities across 300 situational dilemmas, we bypass surface-level alignment.<n>We find substantial variation in adaptability and uncover a consistent phenomenon of latent entanglement.
  arXiv  Detail & Related papers  (2026-05-25T22:20:52Z)
• Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation [58.01855677487771]
  We show that multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes.<n>We propose Cross-lingual Cultural Consistent Preference optimisation (C-3PO), a consensus-driven alignment framework.<n>C-3PO achieves up to a 0.10-point absolute increase in $_S$ over unaligned models, outperforming strong prompting and representation steering baselines.
  arXiv  Detail & Related papers  (2026-04-02T14:04:06Z)
• 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)
• 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)
• Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? [81.49470136653665]
  We evaluate the robustness and expressiveness of value representations across three widely used probing strategies.<n>We show that the demographic context has little effect on the free-text generation, and the models' values only weakly correlate with their preference for value-based actions.
  arXiv  Detail & Related papers  (2025-07-17T18:56:41Z)
• A Dual-Layered Evaluation of Geopolitical and Cultural Bias in LLMs [0.6494933736121663]
  Large language models (LLMs) are increasingly deployed across diverse linguistic and cultural contexts.<n>This paper defines two types of bias in LLMs: model bias (bias stemming from model training) and inference bias (bias induced by the language of the query)<n>We construct a manually curated dataset spanning both factual and disputable QA, across four languages and question types.
  arXiv  Detail & Related papers  (2025-06-27T03:37:15Z)
• From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs [62.9861554207279]
  Adapting cultural values in Large Language Models (LLMs) presents significant challenges.<n>Prior work primarily aligns LLMs with different cultural values using World Values Survey (WVS) data.<n>We investigate WVS-based training for cultural value adaptation and find that relying solely on survey data cane cultural norms and interfere with factual knowledge.
  arXiv  Detail & Related papers  (2025-05-22T09:00:01Z)
• Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs [7.802103248428407]
  We identify and test three assumptions behind current survey-based evaluation methods.<n>We find a high level of instability across presentation formats, incoherence between evaluated versus held-out cultural dimensions, and erratic behavior under prompt steering.
  arXiv  Detail & Related papers  (2025-03-11T17:59:53Z)
• ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning [1.1343849658875087]
  ValuesRAG is a novel framework that integrates cultural and demographic knowledge dynamically during text generation.<n>We evaluate ValuesRAG using 6 diverse regional datasets and show that it consistently outperforms baselines.<n>Our findings underscore the potential of dynamic retrieval-based methods to bridge the gap between global LLM capabilities and localized cultural values.
  arXiv  Detail & Related papers  (2025-01-02T03:26:13Z)
• CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models [59.22460740026037]
  "CIVICS: Culturally-Informed & Values-Inclusive Corpus for Societal impacts" dataset is designed to evaluate the social and cultural variation of Large Language Models (LLMs) We create a hand-crafted, multilingual dataset of value-laden prompts which address specific socially sensitive topics, including LGBTQI rights, social welfare, immigration, disability rights, and surrogacy.
  arXiv  Detail & Related papers  (2024-05-22T20:19:10Z)

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.