English
Related papers

Related papers: ACoRN: Noise-Robust Abstractive Compression in Ret…

200 papers

Robust content moderation requires classification systems that can quickly adapt to evolving policies without costly retraining. We present classification using Retrieval-Augmented Generation (RAG), which shifts traditional classification…

Computation and Language · Computer Science 2025-08-11 Richard Willats , Josh Pennington , Aravind Mohan , Bertie Vidgen

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

Computation and Language · Computer Science 2025-12-10 Vivek Chari , Benjamin Van Durme

Deep learning-based speech enhancement methods have significantly improved speech quality and intelligibility. Convolutional neural networks (CNNs) have been proven to be essential components of many high-performance models. In this paper,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-11 Dahan Wang , Xiaobin Rong , Shiruo Sun , Yuxiang Hu , Changbao Zhu , Jing Lu

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

Information Retrieval · Computer Science 2023-10-24 George Zerveas , Navid Rekabsaz , Daniel Cohen , Carsten Eickhoff

Dense retrieval (DR) has the potential to resolve the query understanding challenge in conversational search by matching in the learned embedding space. However, this adaptation is challenging due to DR models' extra needs for supervision…

Information Retrieval · Computer Science 2021-05-20 Shi Yu , Zhenghao Liu , Chenyan Xiong , Tao Feng , Zhiyuan Liu

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent…

Computation and Language · Computer Science 2026-02-04 Wenhui Tan , Jiaze Li , Jianzhong Ju , Zhenbo Luo , Ruihua Song , Jian Luan

In many application domains, the proliferation of sensors and devices is generating vast volumes of data, imposing significant pressure on existing data analysis and data mining techniques. Nevertheless, an increase in data volume does not…

Machine Learning · Computer Science 2024-10-21 Daniel Riccio , Genoveffa Tortora , Mara Sangiovanni

Generative adversarial networks (GANs) have gained considerable attention owing to their ability to reproduce images. However, they can recreate training images faithfully despite image degradation in the form of blur, noise, and…

Computer Vision and Pattern Recognition · Computer Science 2021-06-24 Takuhiro Kaneko , Tatsuya Harada

Recurrent neural networks (RNNs) have achieved great success in language modeling. However, since the RNNs have fixed size of memory, their memory cannot store all the information about the words it have seen before in the sentence, and…

Computation and Language · Computer Science 2016-11-29 Da-Rong Liu , Shun-Po Chuang , Hung-yi Lee

The quadratic complexity of self-attention constrains Large Language Models (LLMs) in processing long contexts, a capability essential for many advanced applications. Context compression aims to alleviate this computational bottleneck while…

Computation and Language · Computer Science 2025-12-05 Yangning Li , Shaoshen Chen , Yinghui Li , Yankai Chen , Hai-Tao Zheng , Hui Wang , Wenhao Jiang , Philip S. Yu

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

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external documents at inference time, enabling up-to-date knowledge access without costly retraining. However, conventional RAG methods retrieve…

Computation and Language · Computer Science 2025-07-08 Ting-Wen Ko , Jyun-Yu Jiang , Pu-Jen Cheng

Long-context large language models (LC LLMs) combined with retrieval-augmented generation (RAG) hold strong potential for complex multi-hop and large-document tasks. However, existing RAG systems often suffer from imprecise retrieval,…

Computation and Language · Computer Science 2025-05-22 Woosang Lim , Zekun Li , Gyuwan Kim , Sungyoung Ji , HyeonJung Kim , Kyuri Choi , Jin Hyuk Lim , Kyungpyo Park , William Yang Wang

While RAG demonstrates remarkable capabilities in LLM applications, its effectiveness is hindered by the ever-increasing length of retrieved contexts, which introduces information redundancy and substantial computational overhead. Existing…

Computation and Language · Computer Science 2025-10-28 Yixiong Fang , Tianran Sun , Yuling Shi , Xiaodong Gu

To extend the context length of Transformer-based large language models (LLMs) and improve comprehension capabilities, we often face limitations due to computational resources and bounded memory storage capacity. This work introduces a…

Computation and Language · Computer Science 2024-06-11 Chensen Huang , Guibo Zhu , Xuepeng Wang , Yifei Luo , Guojing Ge , Haoran Chen , Dong Yi , Jinqiao Wang

Retrieval-Augmented Generation (RAG) has recently emerged as a method to extend beyond the pre-trained knowledge of Large Language Models by augmenting the original prompt with relevant passages or documents retrieved by an Information…

The performance of automatic speech recognition systems under noisy environments still leaves room for improvement. Speech enhancement or feature enhancement techniques for increasing noise robustness of these systems usually add components…

Computation and Language · Computer Science 2016-09-19 Stefan Braun , Daniel Neil , Shih-Chii Liu

Annotation noise is widespread in datasets, but manually revising a flawed corpus is time-consuming and error-prone. Hence, given the prior knowledge in Pre-trained Language Models and the expected uniformity across all annotations, we…

Computation and Language · Computer Science 2022-05-12 Chang Shu

Neural network models have shown excellent fluency and performance when applied to abstractive summarization. Many approaches to neural abstractive summarization involve the introduction of significant inductive bias, exemplified through…

Computation and Language · Computer Science 2019-09-04 Luke de Oliveira , Alfredo Láinez Rodrigo

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