@inproceedings{chaudhury-etal-2025-epman,
    title = "{E}p{MAN}: Episodic Memory {A}ttentio{N} for Generalizing to Longer Contexts",
    author = "Chaudhury, Subhajit  and
      Das, Payel  and
      Swaminathan, Sarathkrishna  and
      Kollias, Georgios  and
      Nelson, Elliot  and
      Pahwa, Khushbu  and
      Pedapati, Tejaswini  and
      Melnyk, Igor  and
      Riemer, Matthew",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.574/",
    pages = "11696--11708",
    ISBN = "979-8-89176-251-0",
    abstract = "Recent advances in Large Language Models (LLMs) have yielded impressive successes on many language tasks. However, efficient processing of long contexts using LLMs remains a significant challenge. We introduce **EpMAN** {--} a method for processing long contexts in an episodic memory module while holistically attending to semantically-relevant context chunks. Output from episodic attention is then used to reweigh the decoder{'}s self-attention to the stored KV cache of the context during training and generation. When an LLM decoder is trained using **EpMAN**, its performance on multiple challenging single-hop long-context recall and question-answering benchmarks is found to be stronger and more robust across the range from 16k to 256k tokens than baseline decoders trained with self-attention, and popular retrieval-augmented generation frameworks."
}