To enhance the quality of generated stories, recent story generation models have been investigating the utilization of higher-level attributes like plots or commonsense knowledge. The application of prompt-based learning with large language models (LLMs), exemplified by GPT-3, has exhibited remarkable performance in diverse natural language processing (NLP) tasks. This paper conducts a comprehensive investigation, utilizing both automatic and human evaluation, to compare the story generation capacity of LLMs with recent models across three datasets with variations in style, register, and length of stories. The results demonstrate that LLMs generate stories of significantly higher quality compared to other story generation models. Moreover, they exhibit a level of performance that competes with human authors, albeit with the preliminary observation that they tend to replicate real stories in situations involving world knowledge, resembling a form of plagiarism.

Greta Gerwig's hotly-anticipated Barbie movie has finally hit the big screen – and is set to supercharge the cinema industry left decimated by Covid. 'Barbie' – which is competing with Christopher Nolan's Oppenheimer for box office success – stars Australian actress Margot Robbie as the titular character and Ryan Gosling as her boyfriend Ken. Robbie pays tribute to the original doll created by US inventor Ruth Handler, who saw a gap in the market after noticing not many children's dolls resembled adults. Whether Barbie has a positive influence on the kids who play with her has been one of the most contentious issues in the industry since she first hit shelves in 1959. Here, MailOnline looks at the long-lasting effects a Barbie doll can have on a child's development, according to scientific studies.

Russia launched another wave of attacks on the Black Sea port of Odesa early on Sunday, killing one person and wounding 18, including four children, according to Ukrainian officials. A Ukrainian drone attack on the annexed Crimean Peninsula on Saturday blew up an ammunition depot and prompted evacuations along a 5km (3 miles) radius, according to Moscow-installed officials. It also halted road traffic along a bridge connecting Crimea to Russia. Footage shared by state media showed a thick cloud of grey smoke at the site. Russian news agencies quoted the Health Ministry as saying 12 people required medical assistance and four were taken to hospital. Ukraine said its army destroyed an oil depot and Russian army warehouses in the "temporarily occupied" district of Oktiabrske in central Crimea.

However, this can be expensive to collect. Instead, modelbased metrics to measure utterance similarity, such as A common training technique for language models BERTScore (Zhang et al., 2019) and BLEURT (Sellam is teacher forcing (TF). TF attempts to match et al., 2020), provide a cheaper alternative. These are automated human language exactly, even though identical metrics that capture semantic similarity between meanings can be expressed in different ways. This sentences and tend to have a high correlation with human motivates use of sequence-level objectives for dialogue judgment (Zhang et al., 2019; Sellam et al., 2020).

Abstract--News consumption has significantly increased with the growing popularity and use of web-based forums and social media. This sets the stage for misinforming and confusing people. To help reduce the impact of misinformation on users' potential health-related decisions and other intents, it is desired to have machine learning models to detect and combat fake news automatically. This paper proposes a novel transformer-based model using Capsule neural Networks(CapsNet) called X-CapsNet. This model includes a CapsNet with dynamic routing algorithm paralyzed with a size-based classifier for detecting short and long fake news statements. We use two size-based classifiers, a Deep Convolutional Neural Network (DCNN) for detecting long fake news statements and a Multi-Layer Perceptron (MLP) for detecting short news statements. To resolve the problem of representing short news statements, we use indirect features of news created by concatenating the vector of news speaker profiles and a vector of polarity, sentiment, and counting words of news statements. For evaluating the proposed architecture, we use the Covid-19 and the Liar datasets. The results in terms of the F1-score for the Covid-19 dataset and accuracy for the Liar dataset show that models perform better than the state-of-the-art baselines.

Launchpad is a musical instrument that allows users to create and perform music by pressing illuminated buttons. To assist and inspire the design of the Launchpad light effect, and provide a more accessible approach for beginners to create music visualization with this instrument, we proposed the LaunchpadGPT model to generate music visualization designs on Launchpad automatically. Based on the language model with excellent generation ability, our proposed LaunchpadGPT takes an audio piece of music as input and outputs the lighting effects of Launchpad-playing in the form of a video (Launchpad-playing video). We collect Launchpad-playing videos and process them to obtain music and corresponding video frame of Launchpad-playing as prompt-completion pairs, to train the language model. The experiment result shows the proposed method can create better music visualization than random generation methods and hold the potential for a broader range of music visualization applications. Our code is available at https://github.com/yunlong10/LaunchpadGPT/.

Recent work has studied text-to-audio synthesis using large amounts of paired text-audio data. However, audio recordings with high-quality text annotations can be difficult to acquire. In this work, we approach text-to-audio synthesis using unlabeled videos and pretrained language-vision models. We propose to learn the desired text-audio correspondence by leveraging the visual modality as a bridge. We train a conditional diffusion model to generate the audio track of a video, given a video frame encoded by a pretrained contrastive language-image pretraining (CLIP) model. At test time, we first explore performing a zero-shot modality transfer and condition the diffusion model with a CLIP-encoded text query. However, we observe a noticeable performance drop with respect to image queries. To close this gap, we further adopt a pretrained diffusion prior model to generate a CLIP image embedding given a CLIP text embedding. Our results show the effectiveness of the proposed method, and that the pretrained diffusion prior can reduce the modality transfer gap. While we focus on text-to-audio synthesis, the proposed model can also generate audio from image queries, and it shows competitive performance against a state-of-the-art image-to-audio synthesis model in a subjective listening test. This study offers a new direction of approaching text-to-audio synthesis that leverages the naturally-occurring audio-visual correspondence in videos and the power of pretrained language-vision models.

The adoption of Deep Neural Networks (DNNs) has greatly benefited Natural Language Processing (NLP) during the past decade. However, the demands of long document analysis are quite different from those of shorter texts, while the ever increasing size of documents uploaded on-line renders automated understanding of lengthy texts a critical issue. Relevant applications include automated Web mining, legal document review, medical records analysis, financial reports analysis, contract management, environmental impact assessment, news aggregation, etc. Despite the relatively recent development of efficient algorithms for analyzing long documents, practical tools in this field are currently flourishing. This article serves as an entry point into this dynamic domain and aims to achieve two objectives. Firstly, it provides an overview of the relevant neural building blocks, serving as a concise tutorial for the field. Secondly, it offers a brief examination of the current state-of-the-art in long document NLP, with a primary focus on two key tasks: document classification and document summarization. Sentiment analysis for long texts is also covered, since it is typically treated as a particular case of document classification. Consequently, this article presents an introductory exploration of document-level analysis, addressing the primary challenges, concerns, and existing solutions. Finally, the article presents publicly available annotated datasets that can facilitate further research in this area.

The increasing fluency and widespread usage of large language models (LLMs) highlight the desirability of corresponding tools aiding detection of LLM-generated text. In this paper, we identify a property of the structure of an LLM's probability function that is useful for such detection. Specifically, we demonstrate that text sampled from an LLM tends to occupy negative curvature regions of the model's log probability function. Leveraging this observation, we then define a new curvature-based criterion for judging if a passage is generated from a given LLM. This approach, which we call DetectGPT, does not require training a separate classifier, collecting a dataset of real or generated passages, or explicitly watermarking generated text. It uses only log probabilities computed by the model of interest and random perturbations of the passage from another generic pre-trained language model (e.g., T5). We find DetectGPT is more discriminative than existing zero-shot methods for model sample detection, notably improving detection of fake news articles generated by 20B parameter GPT-NeoX from 0.81 AUROC for the strongest zero-shot baseline to 0.95 AUROC for DetectGPT. See https://ericmitchell.ai/detectgpt for code, data, and other project information.

Meta's global policy head, Sir Nick Clegg, has backed calls for an international agency to guide the regulation of artificial intelligence if it becomes autonomous, saying governments globally should avoid "fragmented" laws around the technology. But Clegg downplayed suggestions of payment for content creators like artists or news outlets whose work is scraped to teach chatbots and generative AI, suggesting such information would be available under fair use arrangements. "Creators who lean in to using this technology, rather than trying to block it or slow it down or prevent it from drawing on their own creative output, will in the long run be better placed than those who set their face against this technology," Clegg told Guardian Australia. "We believe we're using [data] entirely in line with existing law. A lot of this data is being transformed in the way it's being deployed by these generative AI models. In the long run, I can't see how you put the genie back in the bottle, given that these models do use publicly available information across the internet, and not unreasonably so."