@inproceedings{cahyawijaya-etal-2025-high,
    title = "High-Dimension Human Value Representation in Large Language Models",
    author = "Cahyawijaya, Samuel  and
      Chen, Delong  and
      Bang, Yejin  and
      Khalatbari, Leila  and
      Wilie, Bryan  and
      Ji, Ziwei  and
      Ishii, Etsuko  and
      Fung, Pascale",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.274/",
    pages = "5303--5330",
    ISBN = "979-8-89176-189-6",
    abstract = "The widespread application of Large Language Models (LLMs) across various tasks and fields has necessitated the alignment of these models with human values and preferences. Given various approaches of human value alignment, such as Reinforcement Learning with Human Feedback (RLHF), constitutional learning, and safety fine-tuning etc., there is an urgent need to understand the scope and nature of human values injected into these LLMs before their deployment and adoption. We propose UniVar, a high-dimensional neural representation of symbolic human value distributions in LLMs, orthogonal to model architecture and training data. This is a continuous and scalable representation, self-supervised from the value-relevant output of 8 LLMs and evaluated on 15 open-source and commercial LLMs. Through UniVar, we visualize and explore how LLMs prioritize different values in 25 languages and cultures, shedding light on the complex interplay between human values and language modeling."
}