English
Related papers

Related papers: Hierarchical Token Prepending: Enhancing Informati…

200 papers

The prefill stage in long-context LLM inference remains a computational bottleneck. Recent token-ranking heuristics accelerate inference by selectively processing a subset of semantically relevant tokens. However, existing methods suffer…

Computation and Language · Computer Science 2026-02-19 Bradley McDanel , Steven Li , Harshit Khaitan

Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly…

Computation and Language · Computer Science 2024-04-19 Pengfei Wu , Jiahao Liu , Zhuocheng Gong , Qifan Wang , Jinpeng Li , Jingang Wang , Xunliang Cai , Dongyan Zhao

Since the emergence of the Large Language Model (LLM), LLM has been widely used in fields such as writing, translating, and searching. However, there is still great potential for LLM-based methods in handling complex tasks such as…

Artificial Intelligence · Computer Science 2025-02-18 Zongyuan Li , Chang Lu , Xiaojie Xu , Runnan Qi , Yanan Ni , Lumin Jiang , Xiangbei Liu , Xuebo Zhang , Yongchun Fang , Kuihua Huang , Xian Guo

Recently, end-to-end memory networks have shown promising results on Question Answering task, which encode the past facts into an explicit memory and perform reasoning ability by making multiple computational steps on the memory. However,…

Information Retrieval · Computer Science 2016-09-29 Jiaming Xu , Jing Shi , Yiqun Yao , Suncong Zheng , Bo Xu , Bo Xu

Compared with standard text, understanding dialogue is more challenging for machines as the dynamic and unexpected semantic changes in each turn. To model such inconsistent semantics, we propose a simple but effective Hierarchical Dialogue…

Computation and Language · Computer Science 2023-05-02 Xiao Liu , Jian Zhang , Heng Zhang , Fuzhao Xue , Yang You

We present a novel hierarchical triplet loss (HTL) capable of automatically collecting informative training samples (triplets) via a defined hierarchical tree that encodes global context information. This allows us to cope with the main…

Computer Vision and Pattern Recognition · Computer Science 2018-10-17 Weifeng Ge , Weilin Huang , Dengke Dong , Matthew R. Scott

Since the amount of information on the internet is growing rapidly, it is not easy for a user to find relevant information for his/her query. To tackle this issue, much attention has been paid to Automatic Document Summarization. The key…

Computation and Language · Computer Science 2019-02-05 Kamal Al-Sabahi , Zhang Zuping , Yang Kang

Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-04 Ruihan Lin , Zezhen Ding , Zean Han , Jiheng Zhang

Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand.…

Computation and Language · Computer Science 2020-10-13 Brian Lester , Daniel Pressel , Amy Hemmeter , Sagnik Ray Choudhury , Srinivas Bangalore

Efficient attention mechanisms enable long-context transformers but often miss globally important tokens, degrading modeling quality. We introduce a pre-scoring framework that assigns a query-independent global importance prior to keys…

Machine Learning · Computer Science 2026-02-10 Zhexiang Li , Haoyu Wang , Yutong Bao , David Woodruff

Temporal point processes (TPPs) have emerged as powerful tools for modeling asynchronous event sequences. While recent advances have extended TPPs to handle textual information, existing approaches are limited in their ability to generate…

Computation and Language · Computer Science 2026-02-03 Jichu Li , Yilun Zhong , Zhiting Li , Feng Zhou , Quyu Kong

Overparameterized large-scale language models have impressive generalization performance of in-context few-shot learning. However, most language models allocate the same amount of parameters or computation to each token, disregarding the…

Computation and Language · Computer Science 2023-11-28 Dewen Zeng , Nan Du , Tao Wang , Yuanzhong Xu , Tao Lei , Zhifeng Chen , Claire Cui

Speculative decoding (SD) has emerged as a promising approach to accelerate LLM inference without sacrificing output quality. Existing SD methods tailored for video-LLMs primarily focus on pruning redundant visual tokens to mitigate the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-14 Qitan Lv , Tianyu Liu , Wen Wu , Xuenan Xu , Bowen Zhou , Feng Wu , Chao Zhang

The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional…

Computation and Language · Computer Science 2021-04-13 Luyang Huang , Shuyang Cao , Nikolaus Parulian , Heng Ji , Lu Wang

Resource limitations often constrain the parameter counts of Large Language Models (LLMs), hindering their performance. While existing methods employ parameter sharing to reuse the same parameter set under fixed budgets, such approaches…

Computation and Language · Computer Science 2025-02-19 Guanghao Li , Wenhao Jiang , Li Shen , Ming Tang , Chun Yuan

Assigning a set of labels to a given text is a classification problem with many real-world applications, such as recommender systems. Two separate research streams address this issue. Hierarchical Text Classification (HTC) focuses on…

Computation and Language · Computer Science 2026-01-27 Nerijus Bertalis , Paul Granse , Ferhat Gül , Florian Hauss , Leon Menkel , David Schüler , Tom Speier , Lukas Galke , Ansgar Scherp

Chain-of-Thought (CoT) prompting has significantly improved the reasoning capabilities of large language models (LLMs). However, conventional CoT often relies on unstructured, flat reasoning chains that suffer from redundancy and suboptimal…

Computation and Language · Computer Science 2026-04-02 Xingshuai Huang , Derek Li , Bahareh Nikpour , Parsa Omidi

Large Language Models (LLMs) incur significant computational and memory costs when processing long prompts, as full self-attention scales quadratically with input length. Token compression aims to address this challenge by reducing the…

Computation and Language · Computer Science 2026-04-23 Zihao Xu , John Harvill , Ziwei Fan , Yizhou Sun , Hao Ding , Hao Wang

The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its success, a critical challenge persists: long tokens, rich…

Computation and Language · Computer Science 2024-11-11 Haoran Lian , Yizhe Xiong , Zijia Lin , Jianwei Niu , Shasha Mo , Hui Chen , Peng Liu , Guiguang Ding

Large Language Models (LLMs) are increasingly evaluated on multiple-choice question answering (MCQA) tasks using *first-token probability* (FTP), which selects the answer option whose initial token has the highest likelihood. While…

Computation and Language · Computer Science 2026-04-06 Silvia Cappelletti , Tobia Poppi , Samuele Poppi , Zheng-Xin Yong , Diego Garcia-Olano , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara