Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values

• URL: http://arxiv.org/abs/2609.08515v1
• Date: Tue, 08 Sep 2026 10:01:32 GMT
• Title: Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values
• Abstract summary: We propose a fine-tuning-free value vector steering method that derives value directions from hidden-state discrepancies.<n>Our method achieves effective CSV steering, supports cross-lingual transfer of value vectors, and generalizes to existing FLAMES and ValuePrism.
• Score: 35.26533029106899
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical priority. However, whether LLMs exhibit consistent value preferences across languages remains underexplored, particularly for culturally grounded values, which are more abstract and difficult to evaluate and align than safety-centric principles. We investigate this issue through Chinese Social Values (CSV), a value system rooted in Chinese culture and comprising $12$ dimensions across national, societal, and personal levels. We construct C-Voices, the first comprehensive multilingual contrastive probe dataset for CSV, with 86,400 dilemma-based instances in six languages, each pairing a CSV-aligned action with a value-conflicting alternative. Building on the contrastive probes of C-Voices, we then propose a fine-tuning-free value vector steering method that derives value directions from hidden-state discrepancies and selectively intervenes on value-sensitive layers during inference. Experiments on six languages show that CSV-oriented preferences are model-dependent and language-sensitive, with the same dilemma eliciting divergent responses across languages. Our method achieves effective CSV steering, supports cross-lingual transfer of value vectors, and generalizes to existing FLAMES and ValuePrism.

Related papers

• Multilingual Refusal Alignment for Safer Large Language Models [53.64286756804503]
  We investigate whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities.<n>We introduce RefusEU, a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models.<n>Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.
  arXiv  Detail & Related papers  (2026-04-24T09:29:14Z)
• Towards Cross-lingual Values Assessment: A Consensus-Pluralism Perspective [47.001227248208856]
  X-Value is a novel Cross-lingual Values Assessment Benchmark designed to assess deep-level values of content from a global perspective.<n>X-Value consists of more than 5,000 QA pairs across 18 languages, systematically organized into 7 core domains grounded in Schwartz's Theory of Basic Human Values.
  arXiv  Detail & Related papers  (2026-02-19T11:41:34Z)
• 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)
• Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties [36.1630542993178]
  Large Language Models (LLMs) are predominantly evaluated on Standard American English (SAE), often overlooking the diversity of global English varieties.<n>We introduce Trans-EnV, a framework that transforms SAE datasets into multiple English varieties to evaluate the linguistic robustness.<n>Our results reveal significant performance disparities, with accuracy decreasing by up to 46.3% on non-standard varieties.
  arXiv  Detail & Related papers  (2025-05-27T08:23:27Z)
• The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context [0.9130277390156759]
  Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations.<n>Despite their widespread deployment, these models exhibit a monolingual bias, raising concerns about the effectiveness of alignment across languages.<n>Current alignment methods predominantly focus on English, leaving it unclear how alignment mechanism generalizes to multilingual settings.
  arXiv  Detail & Related papers  (2025-04-03T15:46:46Z)
• Language Model Alignment in Multilingual Trolley Problems [138.5684081822807]
  Building on the Moral Machine experiment, we develop a cross-lingual corpus of moral dilemma vignettes in over 100 languages called MultiTP.<n>Our analysis explores the alignment of 19 different LLMs with human judgments, capturing preferences across six moral dimensions.<n>We discover significant variance in alignment across languages, challenging the assumption of uniform moral reasoning in AI systems.
  arXiv  Detail & Related papers  (2024-07-02T14:02:53Z)
• 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)
• Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages? [34.38469832305664]
  This paper focuses on human values-related concepts (i.e., value concepts) due to their significance for AI safety. We first empirically confirm the presence of value concepts within LLMs in a multilingual format. Further analysis on the cross-lingual characteristics of these concepts reveals 3 traits arising from language resource disparities.
  arXiv  Detail & Related papers  (2024-02-28T07:18:39Z)
• AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages with Adversarial Examples [51.048234591165155]
  We present AM2iCo, Adversarial and Multilingual Meaning in Context. It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts. Results reveal that current SotA pretrained encoders substantially lag behind human performance.
  arXiv  Detail & Related papers  (2021-04-17T20:23:45Z)

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.