English
Related papers

Related papers: Efficient Listwise Reranking with Compressed Docum…

200 papers

Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content. To overcome these challenges, we propose a two-step framework, Reconstruct before Summarize (RbS), for effective and…

Computation and Language · Computer Science 2023-10-24 Haochen Tan , Han Wu , Wei Shao , Xinyun Zhang , Mingjie Zhan , Zhaohui Hou , Ding Liang , Linqi Song

We introduce the \textit{Extract-Refine-Retrieve-Read} (ERRR) framework, a novel approach designed to bridge the pre-retrieval information gap in Retrieval-Augmented Generation (RAG) systems through query optimization tailored to meet the…

Computation and Language · Computer Science 2025-09-22 Youan Cong , Pritom Saha Akash , Cheng Wang , Kevin Chen-Chuan Chang

This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation. xRAG reinterprets document embeddings in dense retrieval--traditionally used solely for retrieval--as features from the…

Computation and Language · Computer Science 2024-12-10 Xin Cheng , Xun Wang , Xingxing Zhang , Tao Ge , Si-Qing Chen , Furu Wei , Huishuai Zhang , Dongyan Zhao

Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require…

Computation and Language · Computer Science 2026-01-21 Guo Chen , Junjie Huang , Huaijin Xie , Fei Sun , Tao Jia

Large-alphabet strings are common in scenarios such as information retrieval and natural-language processing. The efficient storage and processing of such strings usually introduces several challenges that are not witnessed in…

Data Structures and Algorithms · Computer Science 2024-05-03 Diego Arroyuelo , Gabriel Carmona , Héctor Larrañaga , Francisco Riveros , Carlos Eugenio Rojas-Morales , Erick Sepúlveda

Recent advancements in Large Language Models (LLMs) have significantly improved their performance across various Natural Language Processing (NLP) tasks. However, LLMs still struggle with generating non-factual responses due to limitations…

Computation and Language · Computer Science 2024-09-10 Taeho Hwang , Soyeong Jeong , Sukmin Cho , SeungYoon Han , Jong C. Park

Compressing neural networks is a key step when deploying models for real-time or embedded applications. Factorizing the model's matrices using low-rank approximations is a promising method for achieving compression. While it is possible to…

Machine Learning · Computer Science 2023-10-20 Lucas Maison , Hélion du Mas des Bourboux , Thomas Courtat

Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefiner, an efficient…

Computation and Language · Computer Science 2025-05-16 Jiajie Jin , Xiaoxi Li , Guanting Dong , Yuyao Zhang , Yutao Zhu , Yongkang Wu , Zhonghua Li , Qi Ye , Zhicheng Dou

Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for knowledge injection during large language model (LLM) inference in recent years. However, due to their limited ability to exploit fine-grained inter-document…

Computation and Language · Computer Science 2025-09-09 Weitao Li , Kaiming Liu , Xiangyu Zhang , Xuanyu Lei , Weizhi Ma , Yang Liu

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

Computation and Language · Computer Science 2025-03-10 Giulio Corallo , Orion Weller , Fabio Petroni , Paolo Papotti

Tokenizer is an essential component for large language models (LLMs), and a tokenizer with a high compression rate can improve the model's representation and processing efficiency. However, the tokenizer cannot ensure high compression rate…

Computation and Language · Computer Science 2024-10-08 Shuhao Gu , Mengdi Zhao , Bowen Zhang , Liangdong Wang , Jijie Li , Guang Liu

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…

Computation and Language · Computer Science 2019-08-13 Chen Zheng , Yu Sun , Shengxian Wan , Dianhai Yu

In the field of model compression, choosing an appropriate rank for tensor decomposition is pivotal for balancing model compression rate and efficiency. However, this selection, whether done manually or through optimization-based automatic…

Machine Learning · Computer Science 2025-09-17 Shiyi Luo , Mingshuo Liu , Yifeng Yu , Shangping Ren , Yu Bai

Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ranking. To overcome this challenge, this paper presents BECR…

Information Retrieval · Computer Science 2022-01-07 Yingrui Yang , Yifan Qiao , Jinjin Shao , Mayuresh Anand , Xifeng Yan , Tao Yang

Large language models (LLMs) have recently shown strong reasoning abilities in domains like mathematics, coding, and scientific problem-solving, yet their potential for ranking tasks, where prime examples include retrieval, recommender…

Information Retrieval · Computer Science 2025-10-17 Tao Feng , Zhigang Hua , Zijie Lei , Yan Xie , Shuang Yang , Bo Long , Jiaxuan You

Retrieval-augmented large language models (LLMs) leverage relevant content retrieved by information retrieval systems to generate correct responses, aiming to alleviate the hallucination problem. However, existing retriever-responder…

Computation and Language · Computer Science 2024-06-26 Taolin Zhang , Dongyang Li , Qizhou Chen , Chengyu Wang , Longtao Huang , Hui Xue , Xiaofeng He , Jun Huang

The efficient processing of long context poses a serious challenge for large language models (LLMs). Recently, retrieval-augmented generation (RAG) has emerged as a promising strategy for this problem, as it enables LLMs to make selective…

Computation and Language · Computer Science 2025-02-18 Kun Luo , Zheng Liu , Peitian Zhang , Hongjin Qian , Jun Zhao , Kang Liu

Pairwise re-ranking models predict which of two documents is more relevant to a query and then aggregate a final ranking from such preferences. This is often more effective than pointwise re-ranking models that directly predict a relevance…

Information Retrieval · Computer Science 2022-07-12 Lukas Gienapp , Maik Fröbe , Matthias Hagen , Martin Potthast

The existing Retrieval-Augmented Generation (RAG) systems face significant challenges in terms of cost and effectiveness. On one hand, they need to encode the lengthy retrieved contexts before responding to the input tasks, which imposes…

Computation and Language · Computer Science 2024-09-25 Zheng Liu , Chenyuan Wu , Ninglu Shao , Shitao Xiao , Chaozhuo Li , Defu Lian

In this work, we present a systematic and comprehensive empirical evaluation of state-of-the-art reranking methods, encompassing large language model (LLM)-based, lightweight contextual, and zero-shot approaches, with respect to their…

Computation and Language · Computer Science 2025-08-26 Abdelrahman Abdallah , Bhawna Piryani , Jamshid Mozafari , Mohammed Ali , Adam Jatowt
‹ Prev 1 4 5 6 7 8 10 Next ›