English
Related papers

Related papers: Discourse-Driven Evaluation: Unveiling Factual Inc…

200 papers

This paper presents a data-driven study focusing on analyzing and predicting sentence deletion -- a prevalent but understudied phenomenon in document simplification -- on a large English text simplification corpus. We inspect various…

Computation and Language · Computer Science 2020-08-27 Yang Zhong , Chao Jiang , Wei Xu , Junyi Jessy Li

Accurate text summarization is one of the most common and important tasks performed by Large Language Models, where the costs of human review for an entire document may be high, but the costs of errors in summarization may be even greater.…

Computation and Language · Computer Science 2024-06-21 Alex Chandler , Devesh Surve , Hui Su

Large language models (LLMs) are widely used for long-form text generation. However, factual errors in the responses would undermine their reliability. Despite growing attention to LLM factuality, the effect of response length on factuality…

Computation and Language · Computer Science 2025-05-30 James Xu Zhao , Jimmy Z. J. Liu , Bryan Hooi , See-Kiong Ng

Large Language Models have significantly advanced natural language processing tasks, but remain prone to generating incorrect or misleading but plausible arguments. This issue, known as hallucination, is particularly concerning in…

Computation and Language · Computer Science 2025-12-04 Ahmad Aghaebrahimian

Systematic reviews are crucial for synthesizing scientific evidence but remain labor-intensive, especially when extracting detailed methodological information. Large language models (LLMs) offer potential for automating methodological…

Computation and Language · Computer Science 2025-10-14 Wenqing Zhang , Trang Nguyen , Elizabeth A. Stuart , Yiqun T. Chen

Multi-document summarization entails producing concise synopses of collections of inputs. For some applications, the synopsis should accurately synthesize inputs with respect to a key aspect, e.g., a synopsis of film reviews written about a…

Computation and Language · Computer Science 2024-07-15 Jay DeYoung , Stephanie C. Martinez , Iain J. Marshall , Byron C. Wallace

Extractive summaries are usually presented as lists of sentences with no expected cohesion between them and with plenty of redundant information if not accounted for. In this paper, we investigate the trade-offs incurred when aiming to…

Computation and Language · Computer Science 2024-06-07 Ronald Cardenas , Matthias Galle , Shay B. Cohen

This paper investigates the influence of discourse features on text complexity assessment. To do so, we created two data sets based on the Penn Discourse Treebank and the Simple English Wikipedia corpora and compared the influence of…

Computation and Language · Computer Science 2017-08-22 Elnaz Davoodi , Leila Kosseim

Abstractive summarization has made tremendous progress in recent years. In this work, we perform fine-grained human annotations to evaluate long document abstractive summarization systems (i.e., models and metrics) with the aim of…

Computation and Language · Computer Science 2022-11-01 Huan Yee Koh , Jiaxin Ju , He Zhang , Ming Liu , Shirui Pan

Through the advent of pre-trained language models, there have been notable advancements in abstractive summarization systems. Simultaneously, a considerable number of novel methods for evaluating factual consistency in abstractive…

Computation and Language · Computer Science 2024-10-03 Joonho Yang , Seunghyun Yoon , Byeongjeong Kim , Hwanhee Lee

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

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 rapid increase in unstructured data across various fields has made multi-document comprehension and summarization a critical task. Traditional approaches often fail to capture relevant context, maintain logical consistency, and extract…

Computation and Language · Computer Science 2024-09-30 Aditi Godbole , Jabin Geevarghese George , Smita Shandilya

We suggest an information-theoretic approach for measuring stylistic coordination in dialogues. The proposed measure has a simple predictive interpretation and can account for various confounding factors through proper conditioning. We…

Computation and Language · Computer Science 2015-08-28 Shuyang Gao , Greg Ver Steeg , Aram Galstyan

Despite the prevalence of pretrained language models in natural language understanding tasks, understanding lengthy text such as document is still challenging due to the data sparseness problem. Inspired by that humans develop their ability…

Computation and Language · Computer Science 2023-12-04 Yueguan Wang , Naoki Yoshinaga

In the summarization domain, a key requirement for summaries is to be factually consistent with the input document. Previous work has found that natural language inference (NLI) models do not perform competitively when applied to…

Computation and Language · Computer Science 2021-11-19 Philippe Laban , Tobias Schnabel , Paul N. Bennett , Marti A. Hearst

Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do…

Computation and Language · Computer Science 2018-08-27 Wojciech Kryściński , Romain Paulus , Caiming Xiong , Richard Socher

Content-dense news report important factual information about an event in direct, succinct manner. Information seeking applications such as information extraction, question answering and summarization normally assume all text they deal with…

Computation and Language · Computer Science 2017-04-04 Yinfei Yang , Ani Nenkova

A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability. A natural question is whether such factual errors can be detected automatically. Inspired by…

Computation and Language · Computer Science 2023-05-23 Roi Cohen , May Hamri , Mor Geva , Amir Globerson

Existing long-document question answering systems typically process texts as flat sequences or use heuristic chunking, which overlook the discourse structures that naturally guide human comprehension. We present a discourse-aware…

Information Retrieval · Computer Science 2026-05-08 Huiyao Chen , Yi Yang , Yinghui Li , Meishan Zhang , Baotian Hu , Min Zhang
‹ Prev 1 3 4 5 6 7 10 Next ›