mlsanityData to 14 Oct 2026

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

arXiv 2601.10257 ↗First posted 15 Jan 2026cs.CL cs.AIcited by 1

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

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 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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 7 of its 50 references that are in the map. First posted on arXiv 15 Jan 2026.

Builds on

7 of 50 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models7 Oct
  2. 2025From Training to Generalization: Improving Moral Reasoning Through Pragmatic Inference28 Sep
  3. 2025Moral Reasoning Across Languages: The Critical Role of Low-Resource Languages in LLMs28 Apr

Other references · 4

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2024Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasetscited by 11
  3. 2024Large Language Models as Mirrors of Societal Moral Standardscited by 5
  4. 2025Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languagescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Modelscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning
  2. 2024Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in
  3. 2024Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Test
  4. 2024Language Model Alignment in Multilingual Trolley Problems
  5. 2025Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework
  6. 2026Do Large Language Models Encode Institutional Experience? Evidence from Cross-Linguistic Moral Reasoning Under Ambiguity
  7. 2025Are Rules Meant to be Broken? Understanding Multilingual Moral Reasoning as a Computational Pipeline with UniMoral
  8. 2024Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment