English
Related papers

Related papers: A Study on Token Pruning for ColBERT

200 papers

The ever-increasing size of large language models (LLMs) presents significant challenges for deployment due to their heavy computational and memory requirements. Current model pruning techniques attempt to alleviate these issues by relying…

Computation and Language · Computer Science 2025-03-03 Ayan Sengupta , Siddhant Chaudhary , Tanmoy Chakraborty

Two step document ranking, where the initial retrieval is done by a classical information retrieval method, followed by neural re-ranking model, is the new standard. The best performance is achieved by using transformer-based models as…

Information Retrieval · Computer Science 2020-09-22 Ivan Sekulić , Amir Soleimani , Mohammad Aliannejadi , Fabio Crestani

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Computation and Language · Computer Science 2025-02-21 Lukas Stankevičius , Mantas Lukoševičius

Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost and reduced ability to isolate functionally relevant reasoning. Prior work on compact…

Computation and Language · Computer Science 2026-04-22 Janvijay Singh , Dilek Hakkani-Tür

It has been shown by many researchers that transformers perform as well as convolutional neural networks in many computer vision tasks. Meanwhile, the large computational costs of its attention module hinder further studies and applications…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Fanghui Xue , Biao Yang , Yingyong Qi , Jack Xin

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in visual understanding and reasoning, but they also impose significant computational burdens due to long visual sequence inputs. Recent works address this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Rinyoichi Takezoe , Yaqian Li , Zihao Bo , Anzhou Hou , Mo Guang , Kaiwen Long

Using token representation from bidirectional language models (LMs) such as BERT is still a widely used approach for token-classification tasks. Even though there exist much larger unidirectional LMs such as Llama-2, they are rarely used to…

Computation and Language · Computer Science 2024-12-11 Takumi Goto , Hiroyoshi Nagao , Yuta Koreeda

The most widely used large language models in the social sciences (such as BERT, and its derivatives, e.g. RoBERTa) have a limitation on the input text length that they can process to produce predictions. This is a particularly pressing…

Computation and Language · Computer Science 2025-09-30 Miklós Sebők , Viktor Kovács , Martin Bánóczy , Daniel Møller Eriksen , Nathalie Neptune , Philippe Roussille

Neural network compression methods have enabled deploying large models on emerging edge devices with little cost, by adapting already-trained models to the constraints of these devices. The rapid development of AI-capable edge devices with…

Machine Learning · Computer Science 2019-12-20 Soroosh Khoram , Jing Li

The attention mechanism in text generation is memory-bounded due to its sequential characteristics. Therefore, off-chip memory accesses should be minimized for faster execution. Although previous methods addressed this by pruning…

Hardware Architecture · Computer Science 2024-07-23 Junyoung Park , Myeonggu Kang , Yunki Han , Yanggon Kim , Jaekang Shin , Lee-Sup Kim

Vision Transformers (ViTs) have achieved state-of-the-art performance across various computer vision tasks, but their high computational cost remains a challenge. Token pruning has been proposed to reduce this cost by selectively removing…

Sound · Computer Science 2025-10-27 Taehan Lee , Hyukjun Lee

Service manual documents are crucial to the engineering company as they provide guidelines and knowledge to service engineers. However, it has become inconvenient and inefficient for service engineers to retrieve specific knowledge from…

Computation and Language · Computer Science 2021-06-25 Jia Wei Chong , Zhiyuan Chen , Mei Shin Oh

The evolving capabilities of large language models are accompanied by growing sizes and deployment costs, necessitating effective inference optimisation techniques. We propose a novel pruning method utilising centrality measures from graph…

Machine Learning · Computer Science 2024-12-02 David Hoffmann , Kailash Budhathoki , Matthaeus Kleindessner

Contextual ranking models based on BERT are now well established for a wide range of passage and document ranking tasks. However, the robustness of BERT-based ranking models under adversarial inputs is under-explored. In this paper, we…

Information Retrieval · Computer Science 2022-06-24 Yumeng Wang , Lijun Lyu , Avishek Anand

BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks. However, a major blocking issue of applying BERT to online services is…

Computation and Language · Computer Science 2020-10-22 Yihuan Mao , Yujing Wang , Chufan Wu , Chen Zhang , Yang Wang , Yaming Yang , Quanlu Zhang , Yunhai Tong , Jing Bai

To reduce the inference cost of large language models, model compression is increasingly used to create smaller scalable models. However, little is known about their robustness to minority subgroups defined by the labels and attributes of a…

Machine Learning · Computer Science 2024-03-27 Leonidas Gee , Andrea Zugarini , Novi Quadrianto

Late-interaction retrieval models like ColBERT achieve superior accuracy by enabling token-level interactions, but their computational cost hinders scalability and integration with Approximate Nearest Neighbor Search (ANNS). We introduce…

Information Retrieval · Computer Science 2026-01-15 Ramnath Kumar , Prateek Jain , Cho-Jui Hsieh

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

Computation and Language · Computer Science 2025-02-03 Antoine Simoulin , Namyong Park , Xiaoyi Liu , Grey Yang

Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Kaiyuan Li , Xiaoyue Chen , Chen Gao , Yong Li , Xinlei Chen

Cross-encoders are effective passage and document re-rankers but less efficient than other neural or classic retrieval models. A few previous studies have applied windowed self-attention to make cross-encoders more efficient. However, these…

Information Retrieval · Computer Science 2024-03-21 Ferdinand Schlatt , Maik Fröbe , Matthias Hagen