# Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation

arXiv: https://arxiv.org/abs/2604.08797 · HTML: https://mlsanity.com/paper/2604.08797/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 75 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://mlsanity.com/paper/2412.03304/) (2024)
- [Can Machines Learn Morality? The Delphi Experiment](https://mlsanity.com/paper/2110.07574/) (2021)
- [Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs](https://mlsanity.com/paper/2503.08688/) (2025)
- [Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?](https://mlsanity.com/paper/2501.15463/) (2025)
- [Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas](https://mlsanity.com/paper/2408.06929/) (2024)
- [Extrinsic Evaluation of Cultural Competence in Large Language Models](https://mlsanity.com/paper/2406.11565/) (2024)
- [Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI](https://mlsanity.com/paper/2409.09467/) (2024)
- [A Corpus for Understanding and Generating Moral Stories](https://mlsanity.com/paper/2204.09438/) (2022)
- [ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding](https://mlsanity.com/paper/2411.05049/) (2024)
- [Biased Tales: Cultural and Topic Bias in Generating Children's Stories](https://mlsanity.com/paper/2509.07908/) (2025)
- [NarraBench: A Comprehensive Framework for Narrative Benchmarking](https://mlsanity.com/paper/2510.09869/) (2025)
- [Developing Story: Case Studies of Generative AI's Use in Journalism](https://mlsanity.com/paper/2406.13706/) (2024)
- [Culture is Everywhere: A Call for Intentionally Cultural Evaluation](https://mlsanity.com/paper/2509.01301/) (2025)
- [Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations](https://mlsanity.com/paper/2411.07320/) (2024)
- [MORABLES: A Benchmark for Assessing Abstract Moral Reasoning in LLMs with Fables](https://mlsanity.com/paper/2509.12371/) (2025)
- [MoVa: Towards Generalizable Classification of Human Morals and Values](https://mlsanity.com/paper/2509.24216/) (2025)
- [Perfectly to a Tee: Understanding User Perceptions of Personalized LLM-Enhanced Narrative Interventions](https://mlsanity.com/paper/2409.16732/) (2024)

## Built on by (most cited first, 2 of 2)

- [AI as a Tool for Simulation-Based Experiments in Literary Studies](https://mlsanity.com/paper/2606.02293/) (2026)
- [The Many Morals of AI: The cautionary bias of North American news narratives in global perspective](https://mlsanity.com/paper/2610.18573/) (2026)

## Abstract (arXiv)

Stories are key to transmitting values across cultures, but their interpretation varies across linguistic and cultural contexts. Thus, we introduce multilingual story moral generation as a novel culturally grounded evaluation task. Using a new dataset of human-written story morals collected across 14 language-culture pairs, we compare model outputs with human interpretations via semantic similarity, a human preference survey, and value categorization. We show that frontier models such as GPT-4o and Gemini generate story morals that are semantically similar to human responses and preferred by human evaluators. However, their outputs exhibit markedly less cross-linguistic variation and concentrate on a narrower set of widely shared values. These findings suggest that while contemporary models can approximate central tendencies of human moral interpretation, they struggle to reproduce the diversity that characterizes human narrative understanding. By framing narrative interpretation as an evaluative task, this work introduces a new approach to studying cultural alignment in language models beyond static benchmarks or knowledge-based tests.