paper

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

paperactiveprovisionalsame-lesson-different-story-cross-lingual-reconstruction-of-cultural-narratives-in-large-language-models-6bc6d0b7·1 events·first seen 19h ago

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

More like this (12)

The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models When English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context Learning Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models Automated reproducibility assessments in the social and behavioral sciences using large language models Characterizing Cultural Localization in AI-Generated Stories Words as Difference Makers: How Large Language Models Determine Causal Structure in Text From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures Civil Court Simulation with Large Language Models Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact Unintended Effects of Geographic Conditioning in Large Language Models Language Modeling Loss

Recent events (1)

4arXiv · cs.CL·19h ago·source ↗

Cross-lingual evaluation framework reveals LLMs redistribute cultural narrative structure while preserving semantic meaning

A new arXiv preprint introduces a multilingual evaluation framework using 414 proverbs across 15 languages to assess whether LLMs preserve culturally grounded meaning when generating narratives. Using four LLMs to produce 13k narratives, the study finds that cross-lingual prompting preserves proverb-level semantic meaning but systematically redistributes agency, social positioning, and narrative structure. Strong inter-model convergence across architectures suggests multilingual LLMs rely on shared semantic abstractions. The authors argue that semantic similarity metrics alone overestimate cultural preservation in multilingual evaluations.

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