English
Related papers

Related papers: Correction with Backtracking Reduces Hallucination…

200 papers

The evaluation of abstractive summarization models typically uses test data that is identically distributed as training data. In real-world practice, documents to be summarized may contain input noise caused by text extraction artifacts or…

Computation and Language · Computer Science 2023-12-05 Kundan Krishna , Yao Zhao , Jie Ren , Balaji Lakshminarayanan , Jiaming Luo , Mohammad Saleh , Peter J. Liu

Traditional language models face a challenge from hallucinations. Their very presence casts a large, dangerous shadow over the promising realm of natural language processing. It becomes crucial to understand the various kinds of…

Computation and Language · Computer Science 2025-12-03 Parth Pulkundwar , Vivek Dhanawade , Rohit Yadav , Minal Sonkar , Medha Asurlekar , Sarita Rathod

Pre-trained neural abstractive summarization systems have dominated extractive strategies on news summarization performance, at least in terms of ROUGE. However, system-generated abstractive summaries often face the pitfall of factual…

Computation and Language · Computer Science 2020-10-07 Yue Dong , Shuohang Wang , Zhe Gan , Yu Cheng , Jackie Chi Kit Cheung , Jingjing Liu

Producing a reduced version of a source text, as in generic or focused summarization, inherently involves two distinct subtasks: deciding on targeted content and generating a coherent text conveying it. While some popular approaches address…

Computation and Language · Computer Science 2022-10-25 Aviv Slobodkin , Paul Roit , Eran Hirsch , Ori Ernst , Ido Dagan

Hierarchical Merging is a technique commonly used to summarize very long texts ($>$100K tokens) by breaking down the input into smaller sections, summarizing those sections individually, and then merging or combining those summaries into a…

Computation and Language · Computer Science 2025-08-11 Litu Ou , Mirella Lapata

State-of-the-art abstractive summarization systems frequently hallucinate content that is not supported by the source document, mainly due to noise in the training dataset. Existing methods opt to drop the noisy samples or tokens from the…

Computation and Language · Computer Science 2023-02-20 Meng Cao , Yue Dong , Jingyi He , Jackie Chi Kit Cheung

Although many studies have investigated and reduced hallucinations in large language models (LLMs) for single-document tasks, research on hallucination in multi-document summarization (MDS) tasks remains largely unexplored. Specifically, it…

Computation and Language · Computer Science 2025-04-29 Catarina G. Belem , Pouya Pezeshkpour , Hayate Iso , Seiji Maekawa , Nikita Bhutani , Estevam Hruschka

Recent advancements in large language models (LLMs) have considerably advanced the capabilities of summarization systems. However, they continue to face concerns about hallucinations. While prior work has evaluated LLMs extensively in news…

Computation and Language · Computer Science 2024-06-06 Sanjana Ramprasad , Elisa Ferracane , Zachary C. Lipton

Neural abstractive summarization has been studied in many pieces of literature and achieves great success with the aid of large corpora. However, when encountering novel tasks, one may not always benefit from transfer learning due to the…

Computation and Language · Computer Science 2021-06-01 Yi-Syuan Chen , Hong-Han Shuai

Generation of plausible yet incorrect factual information, termed hallucination, is an unsolved issue in large language models. We study the ability of language models to deliberate on the responses they give in order to correct their…

Computation and Language · Computer Science 2023-09-26 Shehzaad Dhuliawala , Mojtaba Komeili , Jing Xu , Roberta Raileanu , Xian Li , Asli Celikyilmaz , Jason Weston

Lack of factual correctness is an issue that still plagues state-of-the-art summarization systems despite their impressive progress on generating seemingly fluent summaries. In this paper, we show that factual inconsistency can be caused by…

Computation and Language · Computer Science 2024-01-22 Asish Ghoshal , Arash Einolghozati , Ankit Arun , Haoran Li , Lili Yu , Vera Gor , Yashar Mehdad , Scott Wen-tau Yih , Asli Celikyilmaz

Currently used metrics for assessing summarization algorithms do not account for whether summaries are factually consistent with source documents. We propose a weakly-supervised, model-based approach for verifying factual consistency and…

Computation and Language · Computer Science 2019-10-29 Wojciech Kryściński , Bryan McCann , Caiming Xiong , Richard Socher

Patients often face difficulties in understanding their hospitalizations, while healthcare workers have limited resources to provide explanations. In this work, we investigate the potential of large language models to generate patient…

Computation and Language · Computer Science 2024-06-26 Stefan Hegselmann , Shannon Zejiang Shen , Florian Gierse , Monica Agrawal , David Sontag , Xiaoyi Jiang

Synthetically created Cross-Lingual Summarisation (CLS) datasets are prone to include document-summary pairs where the reference summary is unfaithful to the corresponding document as it contains content not supported by the document (i.e.,…

Computation and Language · Computer Science 2024-08-02 Huajian Zhang , Laura Perez-Beltrachini

Software documentation largely consists of short, natural language summaries of the subroutines in the software. These summaries help programmers quickly understand what a subroutine does without having to read the source code him or…

Software Engineering · Computer Science 2020-04-13 Sakib Haque , Alexander LeClair , Lingfei Wu , Collin McMillan

Entity abstract summarization aims to generate a coherent description of a given entity based on a set of relevant Internet documents. Pretrained language models (PLMs) have achieved significant success in this task, but they may suffer…

Computation and Language · Computer Science 2024-03-01 Fangwei Zhu , Peiyi Wang , Zhifang Sui

Large Vision-Language Models often generate hallucinated content that is not grounded in its visual inputs. While prior work focuses on mitigating hallucinations, we instead explore leveraging hallucination correction as a training…

Computer Vision and Pattern Recognition · Computer Science 2025-02-24 Lingjun Zhao , Mingyang Xie , Paola Cascante-Bonilla , Hal Daumé , Kwonjoon Lee

Text summarization and text simplification are two major ways to simplify the text for poor readers, including children, non-native speakers, and the functionally illiterate. Text summarization is to produce a brief summary of the main…

Computation and Language · Computer Science 2017-10-09 Shuming Ma , Xu Sun

Abstractive document summarization is usually modeled as a sequence-to-sequence (Seq2Seq) learning problem. Unfortunately, training large Seq2Seq based summarization models on limited supervised summarization data is challenging. This paper…

Computation and Language · Computer Science 2020-10-13 Yanyan Zou , Xingxing Zhang , Wei Lu , Furu Wei , Ming Zhou

Encoder-decoder models have achieved remarkable success in abstractive text summarization, which aims to compress one or more documents into a shorter version without the loss of the essential content. Unfortunately, these models mostly…

Computation and Language · Computer Science 2021-08-27 Shichao Sun , Wenjie Li