@inproceedings{shen-etal-2025-valuecompass,
    title = "{V}alue{C}ompass: A Framework for Measuring Contextual Value Alignment Between Human and {LLM}s",
    author = "Shen, Hua  and
      Knearem, Tiffany  and
      Ghosh, Reshmi  and
      Yang, Yu-Ju  and
      Clark, Nicholas  and
      Mitra, Tanu  and
      Huang, Yun",
    editor = "Zhang, Chen  and
      Allaway, Emily  and
      Shen, Hua  and
      Miculicich, Lesly  and
      Li, Yinqiao  and
      M'hamdi, Meryem  and
      Limkonchotiwat, Peerat  and
      Bai, Richard He  and
      T.y.s.s., Santosh  and
      Han, Sophia Simeng  and
      Thapa, Surendrabikram  and
      Rim, Wiem Ben",
    booktitle = "Proceedings of the 9th Widening NLP Workshop",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.winlp-main.15/",
    pages = "75--86",
    ISBN = "979-8-89176-351-7",
    abstract = "As AI advances, aligning it with diverse human and societal values grows critical. But how do we define these values and measure AI{'}s adherence to them? We present ValueCompass, a framework grounded in psychological theories, to assess human-AI alignment. Applying it to five diverse LLMs and 112 humans from seven countries across four scenarios{---}collaborative writing, education, public sectors, and healthcare{---}we uncover key misalignments. For example, humans prioritize national security, while LLMs often reject it. Values also shift across contexts, demanding scenario-specific alignment strategies. This work advances AI design by mapping how systems can better reflect societal ethics."
}