Saved in:
Bibliographic Details
Main Authors: An, Sumin, Sung, Junyoung, Park, Wonpyo, Park, Chanjun, Seo, Paul Hongsuck
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.06139
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913851757297664
author An, Sumin
Sung, Junyoung
Park, Wonpyo
Park, Chanjun
Seo, Paul Hongsuck
author_facet An, Sumin
Sung, Junyoung
Park, Wonpyo
Park, Chanjun
Seo, Paul Hongsuck
contents While large language models (LLMs) excel in generating coherent and contextually rich outputs, their capacity to efficiently handle long-form contexts is limited by fixed-length position embeddings. Additionally, the computational cost of processing long sequences increases quadratically, making it challenging to extend context length. To address these challenges, we propose Long-form Context Injection with Recurrent Compression (LCIRC), a method that enables the efficient processing long-form sequences beyond the model's length limit through recurrent compression without retraining the entire model. We further introduce query dependent context modeling, which selectively compresses query-relevant information, ensuring that the model retains the most pertinent content. Our empirical results demonstrate that Query Dependent LCIRC (QD-LCIRC) significantly improves LLM's ability to manage extended contexts, making it well-suited for tasks that require both comprehensive context understanding and query relevance.
format Preprint
id arxiv_https___arxiv_org_abs_2502_06139
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs
An, Sumin
Sung, Junyoung
Park, Wonpyo
Park, Chanjun
Seo, Paul Hongsuck
Computation and Language
While large language models (LLMs) excel in generating coherent and contextually rich outputs, their capacity to efficiently handle long-form contexts is limited by fixed-length position embeddings. Additionally, the computational cost of processing long sequences increases quadratically, making it challenging to extend context length. To address these challenges, we propose Long-form Context Injection with Recurrent Compression (LCIRC), a method that enables the efficient processing long-form sequences beyond the model's length limit through recurrent compression without retraining the entire model. We further introduce query dependent context modeling, which selectively compresses query-relevant information, ensuring that the model retains the most pertinent content. Our empirical results demonstrate that Query Dependent LCIRC (QD-LCIRC) significantly improves LLM's ability to manage extended contexts, making it well-suited for tasks that require both comprehensive context understanding and query relevance.
title LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs
topic Computation and Language
url https://arxiv.org/abs/2502.06139