English
Related papers

Related papers: Boosting Long-Context Management via Query-Guided …

200 papers

Long context compression is a critical research problem due to its significance in reducing the high computational and memory costs associated with LLMs. In this paper, we propose Activation Beacon, a plug-in module for transformer-based…

Computation and Language · Computer Science 2024-10-14 Peitian Zhang , Zheng Liu , Shitao Xiao , Ninglu Shao , Qiwei Ye , Zhicheng Dou

As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce…

Machine Learning · Computer Science 2025-12-24 Tenghui Li , Guoxu Zhou , Xuyang Zhao , Yuning Qiu , Qibin Zhao

In this paper, we propose active recap learning (ARL), a framework for enhancing large language model (LLM) in understanding long contexts. ARL enables models to revisit and summarize earlier content through targeted sequence construction…

Computation and Language · Computer Science 2026-01-21 Chenyu Hui

Long-context Multimodal Large Language Models (MLLMs) demand substantial computational resources for inference as the growth of their multimodal Key-Value (KV) cache, in response to increasing input lengths, challenges memory and time…

Computation and Language · Computer Science 2024-06-27 Zhongwei Wan , Ziang Wu , Che Liu , Jinfa Huang , Zhihong Zhu , Peng Jin , Longyue Wang , Li Yuan

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory…

Computation and Language · Computer Science 2026-05-21 Seonghwan Choi , Beomseok Kang , Dongwon Jo , Jae-Joon Kim

In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints including model sizes and computing resources, the length of…

Computation and Language · Computer Science 2024-12-24 Zhuo Chen , Xinyu Wang , Yong Jiang , Pengjun Xie , Fei Huang , Kewei Tu

Extending context windows (i.e., Long Context, LC) and using retrievers to selectively access relevant information (i.e., Retrieval-Augmented Generation, RAG) are the two main strategies to enable LLMs to incorporate extremely long external…

Computation and Language · Computer Science 2025-01-06 Xinze Li , Yixin Cao , Yubo Ma , Aixin Sun

Long context capability is a crucial competency for large language models (LLMs) as it mitigates the human struggle to digest long-form texts. This capability enables complex task-solving scenarios such as book summarization, code…

Computation and Language · Computer Science 2024-10-10 Jiayi Yuan , Hongyi Liu , Shaochen Zhong , Yu-Neng Chuang , Songchen Li , Guanchu Wang , Duy Le , Hongye Jin , Vipin Chaudhary , Zhaozhuo Xu , Zirui Liu , Xia Hu

The increasing adoption of large language models (LLMs) with extended context windows necessitates efficient Key-Value Cache (KVC) management to optimize inference performance. Inference workloads like Retrieval-Augmented Generation (RAG)…

Emerging Technologies · Computer Science 2025-05-29 Yue Zhu , Hao Yu , Chen Wang , Zhuoran Liu , Eun Kyung Lee

Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across invocations, existing approaches preserve either the agent's trajectory, passive access to…

Artificial Intelligence · Computer Science 2026-05-20 Zhuohan Gu , Qizheng Zhang , Omar Khattab , Samuel Madden

The increasing complexity of AI tasks has shifted the paradigm from monolithic models toward multi-agent large language model (LLM) systems. However, these collaborative architectures introduce a critical bottleneck: redundant prefill…

Machine Learning · Computer Science 2026-03-17 Yingsheng Geng , Yuchong Gao , Weihong Wu , Guyue Liu , Jiang Liu

Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ignored. However, we believe such optimization is crucial,…

Computation and Language · Computer Science 2025-06-04 Jialong Wu , Zhenglin Wang , Linhai Zhang , Yilong Lai , Yulan He , Deyu Zhou

Context-augmented generation (CAG) techniques, including RAG and ICL, require the efficient combination of multiple contexts to generate responses to user queries. Directly inputting these contexts as a sequence introduces a considerable…

Machine Learning · Computer Science 2025-02-13 Xinyu Yang , Tianqi Chen , Beidi Chen

Retrieval-augmented generation (RAG) enhances the capabilities of large language models (LLMs) by incorporating external knowledge into their input prompts. However, when the retrieved context contradicts the LLM's parametric knowledge, it…

Computation and Language · Computer Science 2025-09-29 Eunseong Choi , June Park , Hyeri Lee , Jongwuk Lee

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

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appearing in multiple…

Computation and Language · Computer Science 2025-11-11 Jingbo Yang , Bairu Hou , Wei Wei , Yujia Bao , Shiyu Chang

Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache. Retrieval-based KV cache reduction methods can mitigate these challenges,…

Computation and Language · Computer Science 2025-06-04 Junhui He , Junna Xing , Nan Wang , Rui Xu , Shangyu Wu , Peng Zhou , Qiang Liu , Chun Jason Xue , Qingan Li

Retrieval Augmented Generation (RAG) has emerged as a crucial technique for enhancing the accuracy of Large Language Models (LLMs) by incorporating external information. With the advent of LLMs that support increasingly longer context…

Machine Learning · Computer Science 2024-11-07 Quinn Leng , Jacob Portes , Sam Havens , Matei Zaharia , Michael Carbin

Large Language Models (LLMs) are increasingly deployed in large-scale online services, enabling sophisticated applications. However, the computational overhead of generating key-value (KV) caches in the prefill stage presents a major…

Machine Learning · Computer Science 2025-02-24 Shuowei Jin , Xueshen Liu , Qingzhao Zhang , Z. Morley Mao

Long-context LLMs demand accurate inference at low latency, yet decoding becomes primarily constrained by KV cache as context grows. Prior pruning methods are largely context-agnostic: their token selection ignores step-wise relevance and…

Artificial Intelligence · Computer Science 2026-02-25 Chao Fei , Guozhong Li , Chenxi Liu , Panos Kalnis