Related papers: Correcting Diverse Factual Errors in Abstractive S…
Neural abstractive summarization models make summaries in an end-to-end manner, and little is known about how the source information is actually converted into summaries. In this paper, we define input sentences that contain essential…
We propose a novel text editing task, referred to as \textit{fact-based text editing}, in which the goal is to revise a given document to better describe the facts in a knowledge base (e.g., several triples). The task is important in…
Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples. However, in opinion summarization, large annotated datasets of reviews…
This study presents a controllable abstract summary generation method for large language models based on prompt engineering. To address the issues of summary quality and controllability in traditional methods, we design a multi-stage prompt…
Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vulnerable to…
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…
Recent advances in the field of abstractive summarization leverage pre-trained language models rather than train a model from scratch. However, such models are sluggish to train and accompanied by a massive overhead. Researchers have…
Unsupervised methods are promising for abstractive text summarization in that the parallel corpora is not required. However, their performance is still far from being satisfied, therefore research on promising solutions is on-going. In this…
We introduce 'FactCheck Editor', an advanced text editor designed to automate fact-checking and correct factual inaccuracies. Given the widespread issue of misinformation, often a result of unintentional mistakes by content creators, our…
Models pretrained with self-supervised objectives on large text corpora achieve state-of-the-art performance on English text summarization tasks. However, these models are typically fine-tuned on hundreds of thousands of data points, an…
People nowadays use search engines like Google, Yahoo, and Bing to find information on the Internet. Due to explosion in data, it is helpful for users if they are provided relevant summaries of the search results rather than just links to…
Automatic summarization of legal case judgements, which are known to be long and complex, has traditionally been tried via extractive summarization models. In recent years, generative models including abstractive summarization models and…
Single document news summarization has seen substantial progress on faithfulness in recent years, driven by research on the evaluation of factual consistency, or hallucinations. We ask whether these advances carry over to other text…
In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may contain information that cannot be inferred from the source text. On large news corpora, removing low quality samples has been shown to reduce…
Despite large language models (LLMs) have demonstrated impressive performance in various tasks, they are still suffering from the factual inconsistency problem called hallucinations. For instance, LLMs occasionally generate content that…
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…
One of the most challenging aspects of current single-document news summarization is that the summary often contains 'extrinsic hallucinations', i.e., facts that are not present in the source document, which are often derived via world…
We study the efficacy of fine-tuning Large Language Models (LLMs) for the specific task of report (government archives, news, intelligence reports) summarization. While this topic is being very actively researched - our specific application…
Factuality is important to dialogue summarization. Factual error correction (FEC) of model-generated summaries is one way to improve factuality. Current FEC evaluation that relies on factuality metrics is not reliable and detailed enough.…
It is well-known that abstractive summaries are subject to hallucination---including material that is not supported by the original text. While summaries can be made hallucination-free by limiting them to general phrases, such summaries…