@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://aclanthology.org/2025.acl-long.574/",
doi = "10.18653/v1/2025.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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaudhury-etal-2025-epman">
<titleInfo>
<title>EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Subhajit</namePart>
<namePart type="family">Chaudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Payel</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarathkrishna</namePart>
<namePart type="family">Swaminathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgios</namePart>
<namePart type="family">Kollias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elliot</namePart>
<namePart type="family">Nelson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khushbu</namePart>
<namePart type="family">Pahwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tejaswini</namePart>
<namePart type="family">Pedapati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Melnyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Riemer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">chaudhury-etal-2025-epman</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.574</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.574/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>11696</start>
<end>11708</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts
%A Chaudhury, Subhajit
%A Das, Payel
%A Swaminathan, Sarathkrishna
%A Kollias, Georgios
%A Nelson, Elliot
%A Pahwa, Khushbu
%A Pedapati, Tejaswini
%A Melnyk, Igor
%A Riemer, Matthew
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F chaudhury-etal-2025-epman
%X 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.
%R 10.18653/v1/2025.acl-long.574
%U https://aclanthology.org/2025.acl-long.574/
%U https://doi.org/10.18653/v1/2025.acl-long.574
%P 11696-11708
Markdown (Informal)
[EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts](https://aclanthology.org/2025.acl-long.574/) (Chaudhury et al., ACL 2025)
ACL
- Subhajit Chaudhury, Payel Das, Sarathkrishna Swaminathan, Georgios Kollias, Elliot Nelson, Khushbu Pahwa, Tejaswini Pedapati, Igor Melnyk, and Matthew Riemer. 2025. EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11696–11708, Vienna, Austria. Association for Computational Linguistics.