The paper introduces a multilingual story moral generation task to evaluate cultural alignment in large language models. Using a dataset of human-written story morals from 14 language‑culture pairs, the authors compare model outputs to human interpretations through semantic similarity, a preference survey, and value categorization. They find that advanced models like GPT‑4o and Gemini produce morally similar and preferred responses but show less cross‑linguistic variation, focusing on a narrower set of shared values, indicating a limitation in capturing the diversity of human narrative understanding.
arXiv:2601. 22396v2 Announce Type: replace-cross Abstract: Despite the growing utility of Large Language Models (LLMs) for simulating human behavior, the extent to which these synthetic personas accurately reflect world and moral value systems across different cultural conditionings remains uncertain.
arXiv:2606. 17350v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the generation of high-quality prose, yet the question of whether these models are capable of generating diverse outputs remains contested.
arXiv:2605. 22660v2 Announce Type: replace-cross Abstract: Moral language is subtle and culturally variable, making it difficult to translate faithfully across languages.
arXiv:2609.06611v1 Announce Type: cross Abstract: Assessing the literary quality of narratives requires evaluating interpretive dimensions (cultural representation, emotional depth, and philosophical...
arXiv:2508.06950v4 Announce Type: replace Abstract: Large Language Models (LLMs), such as ChatGPT, are increasingly used in research, ranging from simple writing assistance to complex data annotation...
arXiv:2609.08515v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical pr...
arXiv:2608. 12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs).
arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common...
The study investigates how large language models (LLMs) handle diverse Indian oral traditions, using the Rajasthani Pabuji epic, Tamil Sangam poetry, and Bengali folk tales as case studies. By prompting Claude Sonnet and Gemini with 54 generation requests across generic, culturally specific, and regional-language prompts, the authors measured reference drift and cross-tradition convergence using Sentence‑BERT embeddings. Results show that while outputs stay closer to their own tradition than to others, there is significant cross‑tradition similarity (0.52–0.66), indicating partial homogenisation; moreover, regional‑language prompting consistently reduced fidelity to authentic traditions.
The paper introduces a 12,000-instance dataset of two-option moral dilemmas covering three pairwise value conflicts—Honesty vs. Justice, Justice vs. Autonomy, and Autonomy vs. Honesty—translated into Hindi, Arabic, Spanish, and Chinese to test cross‑lingual behavior. Benchmarking on GPT‑5‑mini shows a consistent preference for Honesty over Autonomy across all languages when no policy is provided, while Llama‑3.2‑1/3B models exhibit a strong first‑option bias that is largely eliminated by plain fine‑tuning or Direct Preference Optimization, raising accuracy above 98%. The authors propose a task vector transfer method that orthogonalizes value preference vectors with respect to general instruction‑following vectors, effectively isolating specific value directions and enabling task arithmetic to flip a model’s stance.
arXiv:2610.28066v1 Announce Type: cross Abstract: Multilingual evaluations often score a model's opening yes or no, a token that also carries model and language answering conventions. We ask when dif...
The paper introduces CAPRI, a dataset of conversations designed to test whether large language models (LLMs) can adapt their responses to users’ cultural backgrounds. Experiments show that while LLMs can infer a user’s cultural context and recall relevant conventions, they frequently fail to apply this knowledge when generating answers unless explicitly prompted to do so. The study also finds that LLMs’ cultural adaptations improve as more cues are provided, yet their default priors are not culture‑neutral and sometimes reflect the model’s country of origin.