English
Related papers

Related papers: Beyond RAG: Task-Aware KV Cache Compression for Co…

200 papers

Considering the limited internal parametric knowledge, retrieval-augmented generation (RAG) has been widely used to extend the knowledge scope of large language models (LLMs). Despite the extensive efforts on RAG research, in existing…

Computation and Language · Computer Science 2024-11-22 Yuhao Wang , Ruiyang Ren , Junyi Li , Wayne Xin Zhao , Jing Liu , Ji-Rong Wen

Large Language Models (LLMs) excel at multi-step reasoning problems with explicit chain-of-thought (CoT), but verbose traces incur significant computational costs and memory overhead, and often carry redundant, stylistic artifacts. Latent…

Machine Learning · Computer Science 2026-05-08 Anna Kuzina , Maciej Pioro , Paul N. Whatmough , Babak Ehteshami Bejnordi

A common way to extend the memory of large language models (LLMs) is by retrieval augmented generation (RAG), which inserts text retrieved from a larger memory into an LLM's context window. However, the context window is typically limited…

Computation and Language · Computer Science 2025-02-14 Marc Pickett , Jeremy Hartman , Ayan Kumar Bhowmick , Raquib-ul Alam , Aditya Vempaty

How to efficiently serve LLMs in practice has become exceptionally challenging due to their prohibitive memory and computation requirements. In this study, we investigate optimizing the KV cache, whose memory footprint poses a critical…

Computation and Language · Computer Science 2025-06-10 Akshat Sharma , Hangliang Ding , Jianping Li , Neel Dani , Minjia Zhang

Large Language Models (LLMs) demonstrate strong reasoning abilities but face limitations such as hallucinations and outdated knowledge. Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) addresses these issues by grounding LLM…

Computation and Language · Computer Science 2025-03-04 Mufei Li , Siqi Miao , Pan Li

Retrieval-augmented generation (RAG) has emerged as an approach to augment large language models (LLMs) by reducing their reliance on static knowledge and improving answer factuality. RAG retrieves relevant context snippets and generates an…

Computation and Language · Computer Science 2025-02-21 Juraj Vladika , Florian Matthes

Recent advancements in Large Visual Language Models (LVLMs) have gained significant attention due to their remarkable reasoning capabilities and proficiency in generalization. However, processing a large number of visual tokens and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Kai Huang , Hao Zou , Bochen Wang , Ye Xi , Zhen Xie , Hao Wang

Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate…

Retrieval-Augmented Generation (RAG) mitigates hallucination in Large Language Models (LLMs) by incorporating external data, with Knowledge Graphs (KGs) offering crucial information for question answering. Traditional Knowledge Graph…

Computation and Language · Computer Science 2025-09-08 Yushi Sun , Kai Sun , Yifan Ethan Xu , Xiao Yang , Xin Luna Dong , Nan Tang , Lei Chen

With reasoning becoming the generative paradigm for large language models (LLMs), the memory bottleneck caused by KV cache during the decoding phase has become a critical factor limiting high-concurrency service. Although existing KV cache…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-11 Mengqi Liao , Lu Wang , Chaoyun Zhang , Bo Qiao , Si Qin , Qingwei Lin , Saravan Rajmohan , Dongmei Zhang , Huaiyu Wan

Reinforcement Learning (RL) has emerged as a crucial paradigm for unlocking the advanced reasoning capabilities of Large Language Models (LLMs), encompassing frameworks like RLHF and RLAIF. Regardless of the specific optimization algorithm…

Machine Learning · Computer Science 2026-05-11 Rui Zhu , Weiheng Bai , Qiushi Wu , Yang Ren , Haixu Tang , Yuchu Liu

The key-value (KV) cache is a major bottleneck in long-context inference, where memory and computation grow with sequence length. Existing KV eviction methods reduce this cost but typically degrade performance relative to full-cache…

Machine Learning · Computer Science 2026-05-12 Ngoc Bui , Hieu Trung Nguyen , Arman Cohan , Rex Ying

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in jointly understanding text, images, and videos, often evaluated via Visual Question Answering (VQA). However, even state-of-the-art MLLMs struggle with…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Alberto Compagnoni , Marco Morini , Sara Sarto , Federico Cocchi , Davide Caffagni , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Large Language Models (LLMs) excel in language tasks but are prone to hallucinations and outdated knowledge. Retrieval-Augmented Generation (RAG) mitigates these by grounding LLMs in external knowledge. However, in complex domains involving…

Computation and Language · Computer Science 2025-08-28 Peiran Zhou , Junnan Zhu , Yichen Shen , Ruoxi Yu

The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV cache. However, loading the entire cache incurs significant…

Computation and Language · Computer Science 2025-05-28 Dingyu Yao , Bowen Shen , Zheng Lin , Wei Liu , Jian Luan , Bin Wang , Weiping Wang

Large Language Models (LLMs) have recently demonstrated remarkable reasoning abilities, yet hallucinate on knowledge-intensive tasks. Retrieval-augmented generation (RAG) mitigates this issue by grounding answers in external sources, e.g.,…

Computation and Language · Computer Science 2026-01-29 Kaehyun Um , KyuHwan Yeom , Haerim Yang , Minyoung Choi , Hyeongjun Yang , Kyong-Ho Lee

Large Language Models (LLMs) have shown remarkable capabilities across diverse tasks, yet they face inherent limitations such as constrained parametric knowledge and high retraining costs. Retrieval-Augmented Generation (RAG) augments the…

Information Retrieval · Computer Science 2025-08-26 Leqian Li , Dianxi Shi , Jialu Zhou , Xinyu Wei , Mingyue Yang , Songchang Jin , Shaowu Yang

Large reasoning models (LRMs) often incur significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning. This incurs both memory overhead and throughput bottlenecks, limiting…

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

Retrieval-Augmented Generation (RAG) has emerged as a prominent method for incorporating domain knowledge into Large Language Models (LLMs). While RAG enhances response relevance by incorporating retrieved domain knowledge in the context,…

Computation and Language · Computer Science 2025-03-28 Kushagra Bhushan , Yatin Nandwani , Dinesh Khandelwal , Sonam Gupta , Gaurav Pandey , Dinesh Raghu , Sachindra Joshi