English
Related papers

Related papers: Parallel Context-of-Experts Decoding for Retrieval…

200 papers

Answering complex, real-world queries often requires synthesizing facts scattered across vast document corpora. In these settings, standard retrieval-augmented generation (RAG) pipelines suffer from incomplete evidence coverage, while…

Computation and Language · Computer Science 2026-03-10 Yagiz Can Akay , Muhammed Yusuf Kartal , Esra Alparslan , Faruk Ortakoyluoglu , Arda Akpinar

Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when analyzing long documents. When long documents are processed sequentially, early or dominant…

Computation and Language · Computer Science 2026-05-21 Aisvarya Adeseye , Jouni Isoaho , Adeyemi Adeseye

Query expansion with pseudo-relevance feedback (PRF) is a powerful approach to enhance the effectiveness in information retrieval. Recently, with the rapid advance of deep learning techniques, neural text generation has achieved promising…

Information Retrieval · Computer Science 2021-08-16 Minghui Huang , Dong Wang , Shuang Liu , Meizhen Ding

Modern serving systems for Mixture-of-Experts (MoE) models adopt hybrid data-expert parallelism: expert parallelism (EP) shards experts across GPUs to scale capacity, while data parallelism (DP) replicates attention layers across instances…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-21 Jiefei Chen , Binbin Lin , Jinming Ma , Jiangfei Duan , Haojie Duanmu , Hao Liu , Qinxiu Cheng , Xiuhong Li , Zhilin Pei , Hui Wang , Xingcheng Zhang , Dahua Lin

Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from semantic drift, limited adaptability, and catastrophic forgetting as new domains emerge.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Wen Wen , Hao Chen , Shiliang Zhang

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

Computation and Language · Computer Science 2025-10-06 Wenrui Bao , Zhiben Chen , Dan Xu , Yuzhang Shang

Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness…

Computation and Language · Computer Science 2024-10-15 Chanwoong Yoon , Taewhoo Lee , Hyeon Hwang , Minbyul Jeong , Jaewoo Kang

Endowing chatbots with a consistent persona is essential to an engaging conversation, yet it remains an unresolved challenge. In this work, we propose a new retrieval-enhanced approach for personalized response generation. Specifically, we…

Computation and Language · Computer Science 2023-06-13 Shuai Liu , Hyundong J. Cho , Marjorie Freedman , Xuezhe Ma , Jonathan May

Retrieval-Augmented Generation (RAG) systems enhance text generation by incorporating external knowledge but often struggle when retrieving context across different text modalities due to semantic gaps. We introduce a generalized…

Machine Learning · Computer Science 2024-11-01 Arihan Yadav , Alan McMillan

Retrieval-augmented generation (RAG) has gained traction as a powerful approach for enhancing language models by integrating external knowledge sources. However, RAG introduces challenges such as retrieval latency, potential errors in…

Computation and Language · Computer Science 2025-02-25 Brian J Chan , Chao-Ting Chen , Jui-Hung Cheng , Hen-Hsen Huang

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

Computation and Language · Computer Science 2024-02-20 Zizhong Li , Haopeng Zhang , Jiawei Zhang

Automated code completion, aiming at generating subsequent tokens from unfinished code, has been significantly benefited from recent progress in pre-trained Large Language Models (LLMs). However, these models often suffer from coherence…

Software Engineering · Computer Science 2024-05-14 Hanzhuo Tan , Qi Luo , Ling Jiang , Zizheng Zhan , Jing Li , Haotian Zhang , Yuqun Zhang

We aim to develop a retrieval-augmented generation (RAG) framework that answers questions over a corpus of visually-rich documents presented in mixed modalities (e.g., charts, tables) and diverse formats (e.g., PDF, PPTX). In this paper, we…

Computation and Language · Computer Science 2025-04-15 Ryota Tanaka , Taichi Iki , Taku Hasegawa , Kyosuke Nishida , Kuniko Saito , Jun Suzuki

Recently, generative retrieval emerges as a promising alternative to traditional retrieval paradigms. It assigns each document a unique identifier, known as DocID, and employs a generative model to directly generate the relevant DocID for…

Information Retrieval · Computer Science 2024-04-16 Peitian Zhang , Zheng Liu , Yujia Zhou , Zhicheng Dou , Fangchao Liu , Zhao Cao

Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or…

Computation and Language · Computer Science 2024-05-07 Zheng Zhao , Emilio Monti , Jens Lehmann , Haytham Assem

Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. While retrieval-augmented generation (RAG) frameworks are widely adopted,…

Software Engineering · Computer Science 2025-03-27 Wenchao Gu , Juntao Chen , Yanlin Wang , Tianyue Jiang , Xingzhe Li , Mingwei Liu , Xilin Liu , Yuchi Ma , Zibin Zheng

Retrieval-augmented generation (RAG) improves large language model reliability by grounding generated responses in external evidence. However, RAG performance depends on the relevance of retrieved passages, the quality of evidence ranking,…

Information Retrieval · Computer Science 2026-05-05 Fariba Afrin Irany , Sampson Akwafuo

Large Language Models cannot reliably acquire new knowledge post-deployment -- even when relevant text resources exist, models fail to transform them into actionable knowledge without retraining. Retrieval-Augmented Generation attempts to…

Neural and Evolutionary Computing · Computer Science 2026-02-19 Qi Sun , Stefan Nielsen , Rio Yokota , Yujin Tang

In recent years, large language models (LLMs) have made remarkable achievements in various domains. However, the untimeliness and cost of knowledge updates coupled with hallucination issues of LLMs have curtailed their applications in…

Machine Learning · Computer Science 2024-05-31 Chunjing Gan , Dan Yang , Binbin Hu , Hanxiao Zhang , Siyuan Li , Ziqi Liu , Yue Shen , Lin Ju , Zhiqiang Zhang , Jinjie Gu , Lei Liang , Jun Zhou

Most multi-modal knowledge graph completion (MMKGC) models use one embedding scorer to do both retrieval over the full entity set and final decision making. We argue that this coupling is a core bottleneck: global high-recall search and…

Artificial Intelligence · Computer Science 2026-04-29 Guanglin Niu , Bo Li