English
Related papers

Related papers: Summary of a Haystack: A Challenge to Long-Context…

200 papers

Training automatic summary fact verifiers often faces the challenge of a lack of human-labeled data. In this paper, we explore alternative way of leveraging Large Language Model (LLM) generated feedback to address the inherent limitation of…

Computation and Language · Computer Science 2024-12-17 Jihwan Oh , Jeonghwan Choi , Nicole Hee-Yeon Kim , Taewon Yun , Hwanjun Song

While the reasoning capabilities of Large Language Models (LLMs) excel in analytical tasks such as mathematics and code generation, their utility for abstractive summarization remains widely assumed but largely unverified. To bridge this…

Computation and Language · Computer Science 2025-12-10 Haohan Yuan , Haopeng Zhang

Multi-document summarization (MDS) is a challenging task, often decomposed to subtasks of salience and redundancy detection, followed by text generation. In this context, alignment of corresponding sentences between a reference summary and…

Computation and Language · Computer Science 2024-06-04 Ori Ernst , Ori Shapira , Aviv Slobodkin , Sharon Adar , Mohit Bansal , Jacob Goldberger , Ran Levy , Ido Dagan

Question Answering (QA) on narrative text poses a unique challenge to current systems, requiring a deep understanding of long, complex documents. However, the reliability of NarrativeQA, the most widely used benchmark in this domain, is…

Computation and Language · Computer Science 2025-10-16 Tommaso Bonomo , Luca Gioffré , Roberto Navigli

Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and question answering, have been developed to aid in…

Artificial Intelligence · Computer Science 2026-04-03 Maxwell J. Jacobson , Daniel Xie , Jackson Shen , Adil Wazeer , Haiyan Wang , Xinghang Zhang , Yexiang Xue

Recent work has shown the promise of learning with human feedback paradigms to produce human-determined high-quality text. Existing works use human feedback to train large language models (LLMs) in general domain abstractive summarization…

Computation and Language · Computer Science 2025-01-07 Zonghai Yao , Benjamin J Schloss , Sai P. Selvaraj

Reliable automatic evaluation of summarization systems is challenging due to the multifaceted and subjective nature of the task. This is especially the case for languages other than English, where human evaluations are scarce. In this work,…

Evaluating the ability of large language models (LLMs) to process lengthy contexts is critical, especially for retrieving query-relevant information embedded within them. We introduce Sequential-NIAH, a benchmark specifically designed to…

Computation and Language · Computer Science 2025-09-23 Yifei Yu , Qian-Wen Zhang , Lingfeng Qiao , Di Yin , Fang Li , Jie Wang , Zengxi Chen , Suncong Zheng , Xiaolong Liang , Xing Sun

Aspect-based summarization has attracted significant attention for its ability to generate more fine-grained and user-aligned summaries. While most existing approaches assume a set of predefined aspects as input, real-world scenarios often…

Computation and Language · Computer Science 2025-10-09 Yong-En Tian , Yu-Chien Tang , An-Zi Yen , Wen-Chih Peng

Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents. Most recent…

Computation and Language · Computer Science 2022-03-16 Bo Pang , Erik Nijkamp , Wojciech Kryściński , Silvio Savarese , Yingbo Zhou , Caiming Xiong

The availability of large-scale datasets has driven the development of neural models that create summaries from single documents, for generic purposes. When using a summarization system, users often have specific intents with various…

Computation and Language · Computer Science 2021-06-02 Yumo Xu , Mirella Lapata

Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries -- which are nearly always in difficult-to-work-with technical domains -- or by using approximate heuristics to extract them from…

Computation and Language · Computer Science 2022-05-24 Alex Wang , Richard Yuanzhe Pang , Angelica Chen , Jason Phang , Samuel R. Bowman

Large language models (LLMs) achieve optimal utility when their responses are grounded in external knowledge sources. However, real-world documents, such as annual reports, scientific papers, and clinical guidelines, frequently combine…

Information Retrieval · Computer Science 2025-12-17 Chi Zhang , Qiyang Chen , Mengqi Zhang

Comprehensive summaries of sessions enable an effective continuity in mental health counseling, facilitating informed therapy planning. Yet, manual summarization presents a significant challenge, diverting experts' attention from the core…

With the recent advances of large language models (LLMs), it is no longer infeasible to build an automated debate system that helps people to synthesise persuasive arguments. Previous work attempted this task by integrating multiple…

Computation and Language · Computer Science 2024-08-21 Hao Li , Yuping Wu , Viktor Schlegel , Riza Batista-Navarro , Tharindu Madusanka , Iqra Zahid , Jiayan Zeng , Xiaochi Wang , Xinran He , Yizhi Li , Goran Nenadic

We propose a scalable, multifactorial experimental framework that systematically probes LLM sensitivity to subtle semantic changes in pairwise document comparison. We analogize this as a needle-in-a-haystack problem: a single semantically…

Computation and Language · Computer Science 2026-04-22 Sinan G. Aksoy , Alexandra A. Sabrio , Erik VonKaenel , Lee Burke

This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point…

Computation and Language · Computer Science 2024-10-01 Xianlong Zeng , Yijing Gao , Fanghao Song , Ang Liu

Recent large language models (LLMs) support long contexts ranging from 128K to 1M tokens. A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a "needle" (relevant…

Computation and Language · Computer Science 2025-07-10 Ali Modarressi , Hanieh Deilamsalehy , Franck Dernoncourt , Trung Bui , Ryan A. Rossi , Seunghyun Yoon , Hinrich Schütze

Online reviews play a pivotal role in influencing consumer decisions across various domains, from purchasing products to selecting hotels or restaurants. However, the sheer volume of reviews -- often containing repetitive or irrelevant…

Computation and Language · Computer Science 2024-10-18 Mir Tafseer Nayeem , Davood Rafiei

Large Multimodal Models (LMMs) have made significant strides in visual question-answering for single images. Recent advancements like long-context LMMs have allowed them to ingest larger, or even multiple, images. However, the ability to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Tsung-Han Wu , Giscard Biamby , Jerome Quenum , Ritwik Gupta , Joseph E. Gonzalez , Trevor Darrell , David M. Chan