Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs

• URL: http://arxiv.org/abs/2601.10257v1
• Date: Thu, 15 Jan 2026 10:26:29 GMT
• Title: Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs
• Abstract summary: 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.
• Score: 10.386888517619997
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When LLMs judge moral dilemmas, do they reach different conclusions in different languages, and if so, why? Two factors could drive such differences: the language of the dilemma itself, or the language in which the model reasons. Standard evaluation conflates these by testing only matched conditions (e.g., English dilemma with English reasoning). We introduce a methodology that separately manipulates each factor, covering also mismatched conditions (e.g., English dilemma with Chinese reasoning), enabling decomposition of their contributions. To study \emph{what} changes, we propose an approach to interpret the moral judgments in terms of Moral Foundations Theory. As a side result, we identify evidence for splitting the Authority dimension into a family-related and an institutional dimension. Applying this methodology to English-Chinese moral judgment with 13 LLMs, we demonstrate its diagnostic power: (1) the framework isolates reasoning-language effects as contributing twice the variance of input-language effects; (2) it detects context-dependency in nearly half of models that standard evaluation misses; and (3) a diagnostic taxonomy translates these patterns into deployment guidance. We release our code and datasets at https://anonymous.4open.science/r/CrossCulturalMoralJudgement.

Related papers

• MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning [9.704767095270453]
  We introduce MCLASH, a multilingual moral decision-making benchmark to capture culturally situated moral intuitions and social norms across languages.<n>Second, we propose MET (Multilingual Ethics with Theory-grounded reasoning), a two-step prompting method built on expert-curated, theory-based grounds.<n>Third, we introduce MET-D (MET-Distillation), which enhances the second step through a self-distillation training stage that requires no external supervision.
  arXiv  Detail & Related papers  (2026-07-13T15:59:25Z)
• Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora [0.6091702876917279]
  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.
  arXiv  Detail & Related papers  (2026-05-21T16:02:15Z)
• Cross-Lingual Stability of LLM Judges Under Controlled Generation: Evidence from Finno-Ugric Languages [0.22009842278462158]
  Cross-lingual evaluation of large language models (LLMs) typically conflates two sources of variance: genuine model performance differences and measurement instability.<n>We investigate evaluation reliability by holding generation conditions constant while varying target language.<n>Our findings suggest that zero-shot judge transfer is unreliable for discourse-level assessment in morphologically rich languages.
  arXiv  Detail & Related papers  (2026-02-02T16:27:32Z)
• 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)
• MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanation [6.477880844490245]
  MFT CXplain is a benchmark dataset for evaluating the moral reasoning of Large Language Models.<n>It comprises 3,000 tweets across Portuguese, Italian, Persian, and English, annotated with binary hate speech labels, moral categories, and text span-level rationales.<n>Our results show a misalignment between LLM outputs and human annotations in moral reasoning tasks.
  arXiv  Detail & Related papers  (2025-06-23T19:44:21Z)
• Under the Shadow of Babel: How Language Shapes Reasoning in LLMs [27.48119976373105]
  We show that large language models internalize the habitual logical structures embedded in different languages.<n>Our study reveals three key findings: (1) LLMs exhibit typologically aligned attention patterns, focusing more on causes and sentence-initial connectives in Chinese, while showing a more balanced distribution in English.
  arXiv  Detail & Related papers  (2025-06-19T09:06:38Z)
• Are Language Models Consequentialist or Deontological Moral Reasoners? [75.6788742799773]
  We focus on a large-scale analysis of the moral reasoning traces provided by large language models (LLMs)<n>We introduce and test a taxonomy of moral rationales to systematically classify reasoning traces according to two main normative ethical theories: consequentialism and deontology.
  arXiv  Detail & Related papers  (2025-05-27T17:51:18Z)
• Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English [66.97110551643722]
  We investigate dialectal disparities in Large Language Models (LLMs) reasoning tasks.<n>We find that LLMs produce less accurate responses and simpler reasoning chains and explanations for AAE inputs.<n>These findings highlight systematic differences in how LLMs process and reason about different language varieties.
  arXiv  Detail & Related papers  (2025-03-06T05:15:34Z)
• Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM Reasoning [50.99811144731619]
  We show that the choice of formal language affects both the syntactic and the semantic reasoning capability.<n>We conclude that on average, context-aware encodings help LLMs to reason, while there is no apparent effect of using comments or markdown syntax.
  arXiv  Detail & Related papers  (2025-02-24T14:49:52Z)
• 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)
• Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogism [62.571419297164645]
  This paper provides a systematic overview of prior works on the logical reasoning ability of large language models for analyzing categorical syllogisms.<n>We first investigate all the possible variations for the categorical syllogisms from a purely logical perspective.<n>We then examine the underlying configurations (i.e., mood and figure) tested by the existing datasets.
  arXiv  Detail & Related papers  (2024-06-26T21:17:20Z)
• Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention [18.439771003766026]
  We study whether multilingual language models (MultiLMs) can transfer logical reasoning abilities to other languages when they are fine-tuned for reasoning in a different language. We demonstrate that although MultiLMs can transfer reasoning ability across languages in a monolingual setting, they struggle to transfer reasoning abilities in a code-switched setting. Following this observation, we propose a novel attention mechanism that uses a dedicated set of parameters to encourage cross-lingual attention in code-switched sequences.
  arXiv  Detail & Related papers  (2023-10-23T18:06:38Z)
• 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)

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.