@inproceedings{mistry-etal-2025-emergence,
    title = "Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training",
    author = "Mistry, Deven Mahesh  and
      Bajaj, Anooshka  and
      Aggarwal, Yash  and
      Maini, Sahaj Singh  and
      Tiganj, Zoran",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.448/",
    pages = "8893--8911",
    ISBN = "979-8-89176-189-6",
    abstract = "We investigate in-context temporal biases in attention heads and transformer outputs. Using cognitive science methodologies, we analyze attention scores and outputs of the GPT-2 models of varying sizes. Across attention heads, we observe effects characteristic of human episodic memory, including temporal contiguity, primacy and recency. Transformer outputs demonstrate a tendency toward in-context serial recall. Importantly, this effect is eliminated after the ablation of the induction heads, which are the driving force behind the contiguity effect. Our findings offer insights into how transformers organize information temporally during in-context learning, shedding light on their similarities and differences with human memory and learning."
}