English
Related papers

Related papers: AWESOME: GPU Memory-constrained Long Document Summ…

200 papers

Recent advances in long-context reasoning abilities of language models led to interesting applications in large-scale multi-document summarization. However, prior work has shown that these long-context models are not effective at their…

Computation and Language · Computer Science 2025-04-18 Adithya Pratapa , Teruko Mitamura

Long document summarization remains a significant challenge for current large language models (LLMs), as existing approaches commonly struggle with information loss, factual inconsistencies, and coherence issues when processing excessively…

Computation and Language · Computer Science 2026-02-06 Weixuan Wang , Minghao Wu , Barry Haddow , Alexandra Birch

Large Language Models (LLMs) demonstrate exceptional capability across diverse tasks. However, their deployment in long-context scenarios is hindered by two challenges: computational inefficiency and redundant information. We propose RAM…

Computation and Language · Computer Science 2026-03-02 Jiwei Tang , Shilei Liu , Zhicheng Zhang , Qingsong Lv , Runsong Zhao , Tingwei Lu , Langming Liu , Haibin Chen , Yujin Yuan , Hai-Tao Zheng , Wenbo Su , Bo Zheng

Semantic parsing of long documents remains challenging due to quadratic growth in pairwise composition and memory requirements. We introduce \textbf{Hierarchical Segment-Graph Memory (HSGM)}, a novel framework that decomposes an input of…

Artificial Intelligence · Computer Science 2025-09-24 Dong Liu , Yanxuan Yu

Abstractive multi document summarization has evolved as a task through the basic sequence to sequence approaches to transformer and graph based techniques. Each of these approaches has primarily focused on the issues of multi document…

Computation and Language · Computer Science 2022-05-10 Aiswarya Sankar , Ankit Chadha

Retrieval augmented generation (RAG) has been widely adopted to help Large Language Models (LLMs) to process tasks involving long documents. However, existing retrieval models are not designed for long document retrieval and fail to address…

Information Retrieval · Computer Science 2026-02-13 David Jiahao Fu , Lam Thanh Do , Jiayu Li , Kevin Chen-Chuan Chang

Large Language Models (LLMs) face fundamental challenges in long-context reasoning: many documents exceed their finite context windows, while performance on texts that do fit degrades with sequence length, necessitating their augmentation…

Artificial Intelligence · Computer Science 2026-02-18 Shreyas Rajesh , Pavan Holur , Chenda Duan , David Chong , Vwani Roychowdhury

Text summarization is a fundamental task in natural language processing (NLP), and the information explosion has made long-document processing increasingly demanding, making summarization essential. Existing research mainly focuses on model…

Abstractive text summarization is integral to the Big Data era, which demands advanced methods to turn voluminous and often long text data into concise but coherent and informative summaries for efficient human consumption. Despite…

Computation and Language · Computer Science 2025-10-08 Jianbin Shen , Christy Jie Liang , Junyu Xuan

Long document question answering is a challenging task due to its demands for complex reasoning over long text. Previous works usually take long documents as non-structured flat texts or only consider the local structure in long documents.…

Computation and Language · Computer Science 2022-10-20 Yuxiang Nie , Heyan Huang , Wei Wei , Xian-Ling Mao

Our analysis of large summarization datasets indicates that redundancy is a very serious problem when summarizing long documents. Yet, redundancy reduction has not been thoroughly investigated in neural summarization. In this work, we…

Computation and Language · Computer Science 2020-12-02 Wen Xiao , Giuseppe Carenini

Most of the existing information extraction frameworks (Wadden et al., 2019; Veysehet al., 2020) focus on sentence-level tasks and are hardly able to capture the consolidated information from a given document. In our endeavour to generate…

Computation and Language · Computer Science 2021-06-22 Debanjana Kar , Sudeshna Sarkar , Pawan Goyal

Large language model (LLM) agents are fundamentally bottlenecked by finite context windows on long-horizon tasks. As trajectories grow, retaining tool outputs and intermediate reasoning in-context quickly becomes infeasible: the working…

Computation and Language · Computer Science 2026-03-05 Zhenting Wang , Huancheng Chen , Jiayun Wang , Wei Wei

Recently, Transformer-based models have been proven effective in the abstractive summarization task by creating fluent and informative summaries. Nevertheless, these models still suffer from the short-range dependency problem, causing them…

Computation and Language · Computer Science 2026-05-13 Thong Nguyen , Anh Tuan Luu , Truc Lu , Tho Quan

Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries. In this paper, we develop a neural abstractive multi-document…

Computation and Language · Computer Science 2020-05-21 Wei Li , Xinyan Xiao , Jiachen Liu , Hua Wu , Haifeng Wang , Junping Du

In neural abstractive summarization field, conventional sequence-to-sequence based models often suffer from summarizing the wrong aspect of the document with respect to the main aspect. To tackle this problem, we propose the task of…

Computation and Language · Computer Science 2018-12-14 Shen Gao , Xiuying Chen , Piji Li , Zhaochun Ren , Lidong Bing , Dongyan Zhao , Rui Yan

Scientific document summarization has been a challenging task due to the long structure of the input text. The long input hinders the simultaneous effective modeling of both global high-order relations between sentences and local…

Computation and Language · Computer Science 2024-05-17 Chenlong Zhao , Xiwen Zhou , Xiaopeng Xie , Yong Zhang

Long-document topic segmentation plays an important role in information retrieval and document understanding, yet existing methods still show clear shortcomings in ultra-long text settings. Traditional discriminative models are constrained…

Computation and Language · Computer Science 2026-03-02 Kaifeng Wu , Junyan Wu , Qiang Liu , Jiarui Zhang , Wen Xu

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

The majority of available text summarization datasets include short-form source documents that lack long-range causal and temporal dependencies, and often contain strong layout and stylistic biases. While relevant, such datasets will offer…

Computation and Language · Computer Science 2022-12-08 Wojciech Kryściński , Nazneen Rajani , Divyansh Agarwal , Caiming Xiong , Dragomir Radev