Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora

• URL: http://arxiv.org/abs/2605.22660v1
• Date: Thu, 21 May 2026 16:02:15 GMT
• Title: Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora
• Abstract summary: Moral language is subtle and culturally variable, making it difficult to translate faithfully across languages.<n>We show that direct translation preserves subtle moral cues well enough to be harvested by cross-lingual machine learning.<n>We demonstrate this for Polish as a representative Slavic language, with expected generalisation to related languages.
• Score: 0.6091702876917279
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Moral language is subtle and culturally variable, making it difficult to translate faithfully across languages. Idiomatic expressions, slang, and cultural references introduce hard-to-avoid translation artifacts. Yet automated moral values classification depends on language-specific annotated corpora that exist almost exclusively in English. We investigate whether LLM-based translation can bridge this gap, taking Polish as a test case. Using $\sim$50k morally-annotated social media posts from a diverse range of topics, we apply a principled four-method validation pipeline: LaBSE cross-lingual embedding similarity, Centered Kernel Alignment (CKA), LLM-as-judge evaluation, and deep learning classifier parity tests. We show that despite shortcomings in handling slang, vulgarity, and culturally-loaded expressions, direct translation preserves subtle moral cues well enough to be harvested by cross-lingual machine learning -- with mean cosine similarity of 0.86 and AUC gaps of 0.01--0.02 across all foundations closing further under fine-tuning of language models. These results demonstrate that machine translation is a practical and cost-effective path to moral values research in languages currently under-resourced in this domain. We demonstrate this for Polish as a representative Slavic language, with expected generalisation to related languages.

Related papers

• VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages [6.468608052089483]
  We introduce VakyArth, the first pragmatic benchmark for Indic languages.<n>VakyArth evaluates models across five phenomena: deixis, speech acts, implicature, social pragmatics, and coherence.<n>We show that automatic translation metrics can miss fluent but pragmatically unfaithful outputs.
  arXiv  Detail & Related papers  (2026-09-01T19:00:32Z)
• 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)
• Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs [10.386888517619997]
  Two factors could drive such differences: the language of the dilemma itself, or the language in which the model reasons.<n>Standard evaluation conflates these by testing only matched conditions.<n>We introduce a methodology that separately manipulates each factor, covering also mismatched conditions.
  arXiv  Detail & Related papers  (2026-01-15T10:26:29Z)
• PragExTra: A Multilingual Corpus of Pragmatic Explicitation in Translation [12.24429799706733]
  We introduce PragExTra, the first multilingual corpus and detection framework for pragmatic explicitation.<n>We identify candidate explicitation cases through null alignments and refined using active learning with human annotation.<n>Our results show that entity and system-level explicitations are most frequent.
  arXiv  Detail & Related papers  (2025-11-04T16:44:57Z)
• One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning [23.56514813420256]
  We investigate how language mediates moral decision-making in Large Language Models (LLMs)<n>Our analysis reveals significant inconsistencies in LLMs' moral judgments across languages, often reflecting cultural misalignment.<n>We distill our insights into a structured typology of moral reasoning errors that calls for more culturally-aware AI.
  arXiv  Detail & Related papers  (2025-09-25T19:14:17Z)
• The Moral Foundations Weibo Corpus [0.0]
  Moral sentiments influence both online and offline environments, shaping behavioral styles and interaction patterns. Existing corpora, while valuable, often face linguistic limitations. This corpus consists of 25,671 Chinese comments on Weibo, encompassing six diverse topic areas.
  arXiv  Detail & Related papers  (2024-11-14T17:32:03Z)
• Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages [55.157295899188476]
  neural machine translation systems learn to map sentences of different languages into a common representation space. In this work, we test this hypothesis by zero-shot translating from unseen languages. We demonstrate that this setup enables zero-shot translation from entirely unseen languages.
  arXiv  Detail & Related papers  (2024-08-05T07:58:58Z)
• Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models [67.19567060894563]
  Pretrained Language Models (PLMs) learn rich cross-lingual knowledge and can be finetuned to perform well on diverse tasks. We present a new study investigating how well PLMs capture cross-lingual word sense with Contextual Word-Level Translation (C-WLT) We find that as the model size increases, PLMs encode more cross-lingual word sense knowledge and better use context to improve WLT performance.
  arXiv  Detail & Related papers  (2023-04-26T19:55:52Z)
• Speaking Multiple Languages Affects the Moral Bias of Language Models [70.94372902010232]
  Pre-trained multilingual language models (PMLMs) are commonly used when dealing with data from multiple languages and cross-lingual transfer. Do the models capture moral norms from English and impose them on other languages? Our experiments demonstrate that, indeed, PMLMs encode differing moral biases, but these do not necessarily correspond to cultural differences or commonalities in human opinions.
  arXiv  Detail & Related papers  (2022-11-14T20:08:54Z)
• Exposing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders [85.80950708769923]
  We probe multilingual language models for the amount of cross-lingual lexical knowledge stored in their parameters, and compare them against the original multilingual LMs. We also devise a novel method to expose this knowledge by additionally fine-tuning multilingual models. We report substantial gains on standard benchmarks.
  arXiv  Detail & Related papers  (2022-04-30T13:23:16Z)
• Does Transliteration Help Multilingual Language Modeling? [0.0]
  We empirically measure the effect of transliteration on Multilingual Language Models. We focus on the Indic languages, which have the highest script diversity in the world. We find that transliteration benefits the low-resource languages without negatively affecting the comparatively high-resource languages.
  arXiv  Detail & Related papers  (2022-01-29T05:48:42Z)
• On the Language Neutrality of Pre-trained Multilingual Representations [70.93503607755055]
  We investigate the language-neutrality of multilingual contextual embeddings directly and with respect to lexical semantics. Our results show that contextual embeddings are more language-neutral and, in general, more informative than aligned static word-type embeddings. We show how to reach state-of-the-art accuracy on language identification and match the performance of statistical methods for word alignment of parallel sentences.
  arXiv  Detail & Related papers  (2020-04-09T19:50:32Z)

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.