English
Related papers

Related papers: No Mean Feat: Simple, Strong Baselines for Context…

200 papers

Retrieval-augmented generation (RAG) systems trained using reinforcement learning (RL) with reasoning are hampered by inefficient context management, where long, noisy retrieved documents increase costs and degrade performance. We introduce…

Computation and Language · Computer Science 2025-10-14 Zhichao Xu , Minheng Wang , Yawei Wang , Wenqian Ye , Yuntao Du , Yunpu Ma , Yijun Tian

Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires…

Machine Learning · Computer Science 2026-02-26 Zeju Li , Yizhou Zhou , Qiang Xu

Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopted a late interaction…

Information Retrieval · Computer Science 2022-03-30 Yingrui Yang , Yifan Qiao , Tao Yang

Efficient long-context processing remains a crucial challenge for contemporary large language models (LLMs), especially in resource-constrained environments. Soft compression architectures promise to extend effective context length by…

Computation and Language · Computer Science 2026-02-16 Julia Belikova , Danila Rozhevskii , Dennis Svirin , Konstantin Polev , Alexander Panchenko

Efficient context compression is crucial for improving the accuracy and scalability of question answering. For the efficiency of Retrieval Augmented Generation, context should be delivered fast, compact, and precise to ensure clue…

Computation and Language · Computer Science 2026-03-11 Thao Do , Dinh Phu Tran , An Vo , Seon Kwon Kim , Daeyoung Kim

Sentence compression is the task of creating a shorter version of an input sentence while keeping important information. In this paper, we extend the task of compression by deletion with the use of contextual embeddings. Different from…

Information Retrieval · Computer Science 2020-06-08 Minh-Tien Nguyen , Bui Cong Minh , Dung Tien Le , Le Thai Linh

Providing extensive context via prompting is vital for leveraging the capabilities of Large Language Models (LLMs). However, lengthy contexts significantly increase inference latency, as the computational cost of self-attention grows…

Artificial Intelligence · Computer Science 2026-02-17 Guojie Liu , Yiqi Wang , Yanfeng Yang , Wenqi Fan , Songlei Jian , Jianfeng Zhang , Jie Yu

This paper is dedicated to an efficient compression of weights and optimizer states (called checkpoints) obtained at different stages during a neural network training process. First, we propose a prediction-based compression approach, where…

Machine Learning · Computer Science 2025-06-16 Yuriy Kim , Evgeny Belyaev

Retrieval-augmented generation (RAG) often suffers from long and noisy retrieved contexts. Prior context compression methods rely on predefined importance metrics or supervised compression models, rather than on the model's own…

Computation and Language · Computer Science 2026-01-27 Yong Zhang , Heng Li , Yanwen Huang , Ning Cheng , Yang Guo , Yun Zhu , Yanmeng Wang , Shaojun Wang , Jing Xiao

Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context. Towards this task, two main architectures have been applied, namely single-encoder (based on concatenation) and…

Computation and Language · Computer Science 2024-02-05 Paweł Mąka , Yusuf Can Semerci , Jan Scholtes , Gerasimos Spanakis

Large Language Model (LLM) agents are increasingly deployed in complex, multi-step workflows involving planning, tool use, reflection, and interaction with external knowledge systems. These workflows generate rapidly expanding contexts that…

Artificial Intelligence · Computer Science 2025-12-22 Kamer Ali Yuksel

Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…

Computation and Language · Computer Science 2025-02-13 Barnaby Schmitt , Alistair Grosvenor , Matthias Cunningham , Clementine Walsh , Julius Pembrokeshire , Jonathan Teel

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…

Computation and Language · Computer Science 2025-09-26 Manlai Liang , Mandi Liu , Jiangzhou Ji , Huaijun Li , Haobo Yang , Yaohan He , Jinlong Li

Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important component of many systems. Existing compression approaches…

Computation and Language · Computer Science 2026-04-28 Yitian Zhou , Chaoning Zhang , Jiaquan Zhang , Zhenzhen Huang , Jinyu Guo , Sung-Ho Bae , Lik-Hang Lee , Caiyan Qin , Yang Yang

This paper presents a context key/value compression method for Transformer language models in online scenarios, where the context continually expands. As the context lengthens, the attention process demands increasing memory and…

Machine Learning · Computer Science 2024-02-07 Jang-Hyun Kim , Junyoung Yeom , Sangdoo Yun , Hyun Oh Song

Using special tokens (e.g., gist, memory, or compressed tokens) to compress context information is a common practice for large language models (LLMs). However, existing approaches often neglect that position encodings inherently induce…

Computation and Language · Computer Science 2025-09-29 Runsong Zhao , Xin Liu , Xinyu Liu , Pengcheng Huang , Chunyang Xiao , Tong Xiao , Jingbo Zhu

Sentence compression reduces the length of text by removing non-essential content while preserving important facts and grammaticality. Unsupervised objective driven methods for sentence compression can be used to create customized models…

Computation and Language · Computer Science 2022-05-18 Demian Gholipour Ghalandari , Chris Hokamp , Georgiana Ifrim

To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity. This work introduces a…

Computation and Language · Computer Science 2024-06-11 Chensen Huang , Guibo Zhu , Xuepeng Wang , Yifei Luo , Guojing Ge , Haoran Chen , Dong Yi , Jinqiao Wang

This work investigates context compression for Large Language Models (LLMs) using learned compression tokens to reduce the memory and computational demands of processing long sequences. We demonstrate that pre-trained LLMs can be fine-tuned…

Computation and Language · Computer Science 2025-11-12 Dmitrii Tarasov , Elizaveta Goncharova , Kuznetsov Andrey

Long context inference presents challenges at the system level with increased compute and memory requirements, as well as from an accuracy perspective in being able to reason over long contexts. Recently, several methods have been proposed…

Computation and Language · Computer Science 2024-07-15 Siddharth Jha , Lutfi Eren Erdogan , Sehoon Kim , Kurt Keutzer , Amir Gholami