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

arXiv: https://arxiv.org/abs/2601.10257 · HTML: https://mlsanity.com/paper/2601.10257/

## Key facts

- Cited by 1 papers 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.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 7 of 7)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets](https://mlsanity.com/paper/2411.11937/) (2024)
- [EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models](https://mlsanity.com/paper/2510.05942/) (2025)
- [Large Language Models as Mirrors of Societal Moral Standards](https://mlsanity.com/paper/2412.00956/) (2024)
- [Moral Reasoning Across Languages: The Critical Role of Low-Resource Languages in LLMs](https://mlsanity.com/paper/2504.19759/) (2025)
- [Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages](https://mlsanity.com/paper/2512.02841/) (2025)
- [From Training to Generalization: Improving Moral Reasoning Through Pragmatic Inference](https://mlsanity.com/paper/2509.24102/) (2025)

## Built on by (most cited first, 1 of 1)

- [Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models](https://mlsanity.com/paper/2606.18142/) (2026)

## 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.