@inproceedings{toshniwal-etal-2022-baked,
    title = "Baked-in State Probing",
    author = "Toshniwal, Shubham  and
      Wiseman, Sam  and
      Livescu, Karen  and
      Gimpel, Kevin",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.findings-emnlp.397/",
    doi = "10.18653/v1/2022.findings-emnlp.397",
    pages = "5430--5435",
    abstract = "Neural language models have been analyzed for their linguistic and extra-linguistic knowledge via probing. Of particular interest has been the following question: how much can a language model trained only on form learn about meaning? Recent work has demonstrated via probing classifiers that in the setting of simple procedural text, where by ``meaning'' we mean the underlying world state, language models have a non-trivial performance on world state tracking. However, our proposed evaluation based on model predictions shows differing results, suggesting that these models are either not capturing the world state or not using it. How do these results change if the model has access to the world state? We explore this alternate setting with access to the underlying world state only during training and investigate ways of ``baking in'' the state knowledge along with the primary task of language modeling. Our proposed approaches allow for state probing during inference simply via text prompts, avoiding any probing classifier machinery. In terms of performance, we show that baking in the state knowledge during training leads to significant improvements in state tracking performance and text generation quality,"
}