@inproceedings{chen-shen-2026-value,
    title = "{VALUE} {ALIGNMENT} {TAX}: Measuring Value Trade-offs in {LLM} Alignment",
    author = "Chen, Jiajun  and
      Shen, Hua",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1749/",
    pages = "35046--35069",
    ISBN = "979-8-89176-395-1",
    abstract = "Existing work on value alignment typically characterizes value relations statically, ignoring how alignment interventions{---}such as prompting, fine-tuning, or preference optimization{---}reshape the broader value system. In practice, aligning a target value can implicitly shift other values, creating value trade-offs that remain largely unmeasured.We introduce the VAT, a framework that quantifies value trade-offs by measuring how alignment-induced changes propagate across interconnected values relative to achieved on-target gain. VAT captures the system-level dynamics of value expression under alignment intervention, enabling evaluation of both intended improvements and unintended side effects.Using a controlled scenario{--}action dataset grounded in Schwartz value theory, we collect paired pre{--}post normative judgments and analyze alignment effects across models, values, and interventions. Results show that alignment often produces uneven and structured co-movement among values, revealing systematic trade-offs between target and non-target values. These effects are largely invisible under conventional target-only evaluation, but become evident via VAT, highlighting process-level alignment risks and offering new insights into the dynamic nature of value alignment in LLMs.Dataset and code are open-sourced."
}