paper-with-me

홈 › Papers

LLMs as Cultural Archives: Cultural Commonsense Knowledge Graph Extraction

2026-01-25 · Junior Cedric Tonga, Chen Cecilia Liu, Iryna Gurevych, Fajri Koto arxiv

Large language models (LLMs) encode rich cultural knowledge learned from diverse web-scale data, offering an unprecedented opportunity to model cultural commonsense at scale. Yet this knowledge remains mostly implicit and unstructured, limiting its interpretability and use. We present an iterative, prompt-based framework for constructing a Cultural Commonsense Knowledge Graph (CCKG) that treats LLMs as cultural archives, systematically eliciting culture-specific entities, relations, and practices and composing them into multi-step inferential chains across languages. We evaluate CCKG on five countries with human judgments of cultural relevance, correctness, and path coherence. We find that the cultural knowledge graphs are better realized in English, even when the target culture is non-English (e.g., Chinese, Indonesian, Arabic), indicating uneven cultural encoding in current LLMs. Augmenting smaller LLMs with CCKG improves performance on cultural reasoning and story generation, with the largest gains from English chains. Our results show both the promise and limits of LLMs as cultural technologies and that chain-structured cultural knowledge is a practical substrate for culturally grounded NLP.

📄 PDF Abstract BibTeX arXiv:2601.17971

Code (0)

등록된 구현이 없습니다.

Tasks

Story GenerationKnowledge Graphs

Similar Papers 제목 키워드 기반

Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense

2024-05-07 · Siqi Shen, Lajanugen Logeswaran, Moontae Lee, Honglak Lee 외

Large language models (LLMs) have demonstrated substantial commonsense understanding through numerous benchmark evaluations. However, their understanding of cultural commonsense remains largely unexamined. In this paper,…

Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset

2025-09-29 · Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka arxiv

Large language models (LLMs) exhibit social biases, prompting the development of various debiasing methods. However, debiasing methods may degrade the capabilities of LLMs. Previous research has evaluated the impact of b…

CultureTalk-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages

2026-07-23 · Muhammad Dehan Al Kautsar, Salsabila Pranida, Bilal Elbouardi, Fajri Koto arxiv

Culture is lived through conversation, yet existing Indonesian cultural commonsense benchmarks evaluate LLMs on short and isolated prompts, stripping away the dialogic context in which cultural nuances actually surface. …

Machine Translation

Cultural Commonsense Knowledge for Intercultural Dialogues

2024-02-16 · Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum

Despite recent progress, large language models (LLMs) still face the challenge of appropriately reacting to the intricacies of social and cultural conventions. This paper presents MANGO, a methodology for distilling high…

Knowledge DistillationSpecificity

Cross-Cultural Transfer of Commonsense Reasoning in LLMs: Evidence from the Arab World

2025-09-23 · Saeed Almheiri, Rania Hossam, Mena Attia, Chenxi Wang 외 arxiv

Large language models (LLMs) often reflect Western-centric biases, limiting their effectiveness in diverse cultural contexts. Although some work has explored cultural alignment, the potential for cross-cultural transfer,…