# Same Lesson, Different Story: Cross-Lingual Reconstruction of Cultural Narratives in Large Language Models

arXiv: https://arxiv.org/abs/2606.24610 · HTML: https://mlsanity.com/paper/2606.24610/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 13 of 13)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)](https://mlsanity.com/paper/2510.22954/) (2025)
- [Modeling Naive Psychology of Characters in Simple Commonsense Stories](https://mlsanity.com/paper/1805.06533/) (2018)
- [PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian](https://mlsanity.com/paper/2502.07459/) (2025)
- [Towards Geo-Culturally Grounded LLM Generations](https://mlsanity.com/paper/2502.13497/) (2025)
- [Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children's Fairy Tales](https://mlsanity.com/paper/2305.16641/) (2023)
- [Directional Alignment and Narrative Agency in Human-LLM Co-Writing](https://mlsanity.com/paper/2604.23676/) (2026)
- [Culturally-Nuanced Story Generation for Reasoning in Low-Resource Languages: The Case of Javanese and Sundanese](https://mlsanity.com/paper/2502.12932/) (2025)
- [EMBRACE: Shaping Inclusive Opinion Representation by Aligning Implicit Conversations with Social Norms](https://mlsanity.com/paper/2507.20264/) (2025)
- [MATCHA: Matching Text via Contrastive Semantic Alignment](https://mlsanity.com/paper/2605.27345/) (2026)

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

- [Wisdom in Unity: The Role of Multilingual Training in Figurative Language Identification in Proverbs](https://mlsanity.com/paper/2608.08090/) (2026)

## Abstract (arXiv)

The evaluation of cultural grounding context becomes complex when multiple cultures convey the same moral lesson. This challenge is particularly relevant to large language models (LLMs), which produce narratives across a wide range of languages and cultural contexts. However, it remains uncertain whether these models preserve culturally grounded meaning when equivalent moral lessons are conveyed through distinct cultural forms. This study introduces a multilingual evaluation narrative framework that integrates a cross-linguistic collection of 414 proverbs spanning 15 languages and uses four LLMs to generate 13k narratives. By employing semantically equivalent proverbs as culturally grounded prompts, the analysis assesses whether models preserve meaning across languages, how cross-lingual conditioning influences narrative realization, and whether different model families converge on similar interpretations. Results indicate that cross-lingual prompting largely preserves proverb-level semantic meaning while systematically redistributing agency, social positioning, and narrative structure. Additionally, strong inter-model convergence is observed in both monolingual and cross-lingual settings, suggesting that multilingual LLMs rely on shared semantic abstractions despite architectural and linguistic differences. These findings shed light on the need for more comprehensive evaluations of cultural grounding. Relying exclusively on semantic similarity in multilingual narrative assessments may overestimate cultural preservation by neglecting culturally meaningful variations in narrative expression.