@inproceedings{yao-etal-2025-language-models,
    title = "Language models can learn implicit multi-hop reasoning, but only if they have lots of training data",
    author = "Yao, Yuekun  and
      Du, Yupei  and
      Zhu, Dawei  and
      Hahn, Michael  and
      Koller, Alexander",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.490/",
    pages = "9695--9713",
    ISBN = "979-8-89176-332-6",
    abstract = "Implicit reasoning is the ability of a language model to solve multi-hop reasoning tasks in a single forward pass, without chain of thought.We investigate this capability using GPT2-style language models trained from scratch on controlled $k$-hop reasoning datasets ($k = 2, 3, 4$). We show that while such models can indeed learn implicit $k$-hop reasoning,the required training data grows exponentially in $k$, and the requirednumber of transformer layers grows linearly in $k$.We offer a theoretical explanation for why this depth growth is necessary.We further find that the data requirement can be mitigated, but not eliminated,through curriculum learning."
}