Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning
Haijiang Liu, Qiyuan Li, Chao Gao, Yong Cao, Xiangyu Xu, Xun Wu, Daniel Hershcovich, Jinguang Gu
Abstract
Introducing MARK, the Multi-stAge Reasoning frameworK for cultural value survey response simulation, designed to enhance the accuracy, steerability, and interpretability of large language models in this task. The system is inspired by the type dynamics theory in the MBTI psychological framework for personality research. It effectively predicts and utilizes human demographic information for simulation: life-situational stress analysis, group-level personality prediction, and self-weighted cognitive imitation. Experiments on the World Values Survey show that MARK outperforms existing baselines by 10% accuracy and reduces the divergence between model predictions and human preferences. This highlights the potential of our framework to improve zero-shot personalization and help social scientists interpret model predictions. 1
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers1
Ask how each one uses itBuilds on4
- Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject StudiesGati V. Aher, Rosa I. Arriaga, Adam Tauman KalaiICML 2023 · 651 citations
- Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language ModelsMyra Cheng, Esin Durmus, Dan JurafskyACL 2023 · 89 citations
- Investigating Cultural Alignment of Large Language ModelsBadr AlKhamissi, Muhammad N. ElNokrashy, Mai Alkhamissi, Mona T. DiabACL 2024 · 27 citations
- Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language RepresentationsArturo Oncevay, Barry Haddow, Alexandra BirchEMNLP 2020 · 1 citation
Related papers
- Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent ReasoningWonduk Seo, Wonseok Choi, Junseo Koh, Juhyeon Lee et al.ICML 2026 · 2 citations
- SimVBG: Simulating Individual Values by Backstory GenerationBangde Du, Ziyi Ye, Zhijing Wu, Monika Jankowska et al.EMNLP 2025 · 2 citations
- Parametric Social Identity Injection and Diversification in Public Opinion SimulationHexi Wang, Yujia Zhou, Bangde Du, Qingyao Ai et al.KDD 2026 · 2 citations
- Human Simulacra: Benchmarking the Personification of Large Language ModelsQiujie Xie, Qiming Feng, Tianqi Zhang, Qingqiu Li et al.ICLR 2025
- MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent SystemsXuanming Zhang, Yuxuan Chen, Samuel (Min-Hsuan) Yeh, Sharon LiNeurIPS 2025 · 14 citations
