English
Related papers

Related papers: Compress, Gather, and Recompute: REFORMing Long-Co…

200 papers

Memory retention challenges in deep neural architectures have ongoing limitations in the ability to process and recall extended contextual information. Token dependencies degrade as sequence length increases, leading to a decline in…

Computation and Language · Computer Science 2025-03-26 Frederick Dillon , Gregor Halvorsen , Simon Tattershall , Magnus Rowntree , Gareth Vanderpool

Increasing the input length has been a driver of progress in language modeling with transformers. We identify conditions where shorter inputs are not harmful, and achieve perplexity and efficiency improvements through two new methods that…

Computation and Language · Computer Science 2021-06-04 Ofir Press , Noah A. Smith , Mike Lewis

Transformer-based large language models (LLMs) cache context as key-value (KV) pairs during inference. As context length grows, KV cache sizes expand, leading to substantial memory overhead and increased attention latency. This paper…

Databases · Computer Science 2025-10-01 Jang-Hyun Kim , Jinuk Kim , Sangwoo Kwon , Jae W. Lee , Sangdoo Yun , Hyun Oh Song

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks. However, their deployment in long context scenarios remains hindered by computational inefficiency and information redundancy. Context compression…

Computation and Language · Computer Science 2026-03-09 Jiwei Tang , Shilei Liu , Zhicheng Zhang , Yujin Yuan , Libin Zheng , Wenbo Su , Bo Zheng

Large language models (LLMs) often incorporate multiple text chunks in their inputs to provide the necessary contexts. To speed up the prefill of the long LLM inputs, one can pre-compute the KV cache of a text and re-use the KV cache when…

Machine Learning · Computer Science 2025-04-07 Jiayi Yao , Hanchen Li , Yuhan Liu , Siddhant Ray , Yihua Cheng , Qizheng Zhang , Kuntai Du , Shan Lu , Junchen Jiang

Current Large Language Models (LLMs) face inherent limitations due to their pre-defined context lengths, which impede their capacity for multi-hop reasoning within extensive textual contexts. While existing techniques like…

Computation and Language · Computer Science 2024-06-19 Weizhi Fei , Xueyan Niu , Guoqing Xie , Yanhua Zhang , Bo Bai , Lei Deng , Wei Han

Retrieval-augmented generation (RAG) has become a transformative approach for enhancing large language models (LLMs) by grounding their outputs in external knowledge sources. Yet, a critical question persists: how can vast volumes of…

Information Retrieval · Computer Science 2025-04-29 Carlo Merola , Jaspinder Singh

Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…

Computation and Language · Computer Science 2025-02-18 Kun-Hui Lee , Eunhwan Park , Donghoon Han , Seung-Hoon Na

Managing extensive context remains a critical bottleneck for Large Language Models (LLMs), particularly in applications like long-document question answering and autonomous agents where lengthy inputs incur high computational costs and…

Computation and Language · Computer Science 2026-01-06 Yiqing Zhou , Yu Lei , Shuzheng Si , Qingyan Sun , Wei Wang , Yifei Wu , Hao Wen , Gang Chen , Fanchao Qi , Maosong Sun

Retrieved documents containing noise will hinder RAG from detecting answer clues and make the inference process slow and expensive. Therefore, context compression is necessary to enhance its accuracy and efficiency. Existing context…

Computation and Language · Computer Science 2026-04-28 Qianchi Zhang , Hainan Zhang , Liang Pang , Hongwei Zheng , Zhiming Zheng

Transformers have emerged as the backbone of large language models (LLMs). However, generation remains inefficient due to the need to store in memory a cache of key-value representations for past tokens, whose size scales linearly with the…

Computation and Language · Computer Science 2024-07-24 Piotr Nawrot , Adrian Łańcucki , Marcin Chochowski , David Tarjan , Edoardo M. Ponti

In this paper, we introduce Writing in the Margins (WiM), a new inference pattern for Large Language Models designed to optimize the handling of long input sequences in retrieval-oriented tasks. This approach leverages the chunked prefill…

Computation and Language · Computer Science 2024-08-28 Melisa Russak , Umar Jamil , Christopher Bryant , Kiran Kamble , Axel Magnuson , Mateusz Russak , Waseem AlShikh

Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose LLoCO, a…

Computation and Language · Computer Science 2024-10-18 Sijun Tan , Xiuyu Li , Shishir Patil , Ziyang Wu , Tianjun Zhang , Kurt Keutzer , Joseph E. Gonzalez , Raluca Ada Popa

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Junwan Kim , Hyunkyung Bae

Large language models (LLMs) support long-context inference but suffer from substantial memory and runtime overhead due to Key-Value (KV) Cache growth. Existing KV Cache eviction methods primarily rely on local attention weights, neglecting…

Computation and Language · Computer Science 2026-05-11 Tho Mai , Joo-Young Kim

The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this amplified context can…

Software Engineering · Computer Science 2024-02-26 Ming Liang , Xiaoheng Xie , Gehao Zhang , Xunjin Zheng , Peng Di , wei jiang , Hongwei Chen , Chengpeng Wang , Gang Fan

In this work, we present a generalized formulation of the Transformer algorithm by reinterpreting its core mechanisms within the framework of Path Integral formalism. In this perspective, the attention mechanism is recast as a process that…

High Energy Physics - Phenomenology · Physics 2025-05-02 Won-Gi Paeng , Daesuk Kwon , Kyungwon Jeong , Honggyo Suh

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained…

Computation and Language · Computer Science 2024-02-16 Wenxiao Wang , Wei Chen , Yicong Luo , Yongliu Long , Zhengkai Lin , Liye Zhang , Binbin Lin , Deng Cai , Xiaofei He

This paper addresses the challenge of comprehending very long contexts in Large Language Models (LLMs) by proposing a method that emulates Retrieval Augmented Generation (RAG) through specialized prompt engineering and chain-of-thought…

Computation and Language · Computer Science 2025-02-19 Joon Park , Kyohei Atarashi , Koh Takeuchi , Hisashi Kashima

Large Language Models (LLMs) are increasingly deployed across edge and cloud platforms for real-time question-answering and retrieval-augmented generation. However, processing lengthy contexts in distributed systems incurs high…

Computation and Language · Computer Science 2025-05-19 Camille Couturier , Spyros Mastorakis , Haiying Shen , Saravan Rajmohan , Victor Rühle