@inproceedings{heinzerling-inui-2024-monotonic,
    title = "Monotonic Representation of Numeric Attributes in Language Models",
    author = "Heinzerling, Benjamin  and
      Inui, Kentaro",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.acl-short.18/",
    doi = "10.18653/v1/2024.acl-short.18",
    pages = "175--195",
    abstract = "Language models (LMs) can express factual knowledge involving numeric properties such as Karl Popper was born in 1902. However, how this information is encoded in the model{'}s internal representations is not understood well. Here, we introduce a method for finding and editing representations of numeric properties such as an entity{'}s birth year. We find directions that encode numeric properties monotonically, in an interpretable fashion. When editing representations along these directions, LM output changes accordingly. For example, by patching activations along a ``birthyear'' direction we can make the LM express an increasingly late birthyear. Property-encoding directions exist across several numeric properties in all models under consideration, suggesting the possibility that monotonic representation of numeric properties consistently emerges during LM pretraining.Code: https://github.com/bheinzerling/numeric-property-reprA long version of this short paper is available at: https://arxiv.org/abs/2403.10381"
}