Narratives serve as fundamental frameworks in our understanding of the world and play a crucial role in collaborative sensemaking, providing a versatile foundation for sensemaking. Framing is a subtle yet potent mechanism that influences public perception through specific word choices, shaping interpretations of reported news events. Despite the recognized importance of narratives and framing, a significant gap exists in the literature with regard to the explicit consideration of framing within the context of computational extraction and representation. This article explores the capabilities of a specific narrative extraction and representation approach -- narrative maps -- to capture framing information from news data. The research addresses two key questions: (1) Does the narrative extraction method capture the framing distribution of the data set? (2) Does it produce a representation with consistent framing? Our results indicate that while the algorithm captures framing distributions, achieving consistent framing across various starting and ending events poses challenges. Our results highlight the potential of narrative maps to provide users with insights into the intricate framing dynamics within news narratives. However, we note that directly leveraging framing information in the computational narrative extraction process remains an open challenge.

Despite the longstanding adage "an image is worth a thousand words," creating accurate and hyper-detailed image descriptions for training Vision-Language models remains challenging. Current datasets typically have web-scraped descriptions that are short, low-granularity, and often contain details unrelated to the visual content. As a result, models trained on such data generate descriptions replete with missing information, visual inconsistencies, and hallucinations. To address these issues, we introduce ImageInWords (IIW), a carefully designed human-in-the-loop annotation framework for curating hyper-detailed image descriptions and a new dataset resulting from this process. We validate the framework through evaluations focused on the quality of the dataset and its utility for fine-tuning with considerations for readability, comprehensiveness, specificity, hallucinations, and human-likeness. Our dataset significantly improves across these dimensions compared to recently released datasets (+66%) and GPT-4V outputs (+48%). Furthermore, models fine-tuned with IIW data excel by +31% against prior work along the same human evaluation dimensions. Given our fine-tuned models, we also evaluate text-to-image generation and vision-language reasoning. Our model's descriptions can generate images closest to the original, as judged by both automated and human metrics. We also find our model produces more compositionally rich descriptions, outperforming the best baseline by up to 6% on ARO, SVO-Probes, and Winoground datasets.

Methods for relation extraction from text mostly focus on high precision, at the cost of limited recall. High recall is crucial, though, to populate long lists of object entities that stand in a specific relation with a given subject. Cues for relevant objects can be spread across many passages in long texts. This poses the challenge of extracting long lists from long texts. We present the L3X method which tackles the problem in two stages: (1) recall-oriented generation using a large language model (LLM) with judicious techniques for retrieval augmentation, and (2) precision-oriented scrutinization to validate or prune candidates. Our L3X method outperforms Figure 1: Example for extracting long lists from long LLM-only generations by a substantial texts. For the subject "Harry Potter", we aim to extract margin.

In today's technologically driven world, the rapid spread of fake news, particularly during critical events like elections, poses a growing threat to the integrity of information. To tackle this challenge head-on, we introduce FakeWatch, a comprehensive framework carefully designed to detect fake news. Leveraging a newly curated dataset of North American election-related news articles, we construct robust classification models. Our framework integrates a model hub comprising of both traditional machine learning (ML) techniques, and state-of-the-art Language Models (LMs) to discern fake news effectively. Our objective is to provide the research community with adaptable and precise classification models adept at identifying fake news for the elections agenda. Quantitative evaluations of fake news classifiers on our dataset reveal that, while state-of-the-art LMs exhibit a slight edge over traditional ML models, classical models remain competitive due to their balance of accuracy and computational efficiency. Additionally, qualitative analyses shed light on patterns within fake news articles. We provide our labeled data at https://huggingface.co/datasets/newsmediabias/fake_news_elections_labelled_data and model https://huggingface.co/newsmediabias/FakeWatch for reproducibility and further research.

Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in leading open-source LLMs, including Llama, OPT, and T5. We assess the impact of model size, structure, and fine-tuning strategies on their resistance to adversarial perturbations. Our comprehensive evaluation across five diverse text classification tasks establishes a new benchmark for LLM robustness. The findings of this study have far-reaching implications for the reliable deployment of LLMs in real-world applications and contribute to the advancement of trustworthy AI systems.

Last January, not long after agreeing with an actual Nazi that western Jews have brought antisemitism upon themselves by welcoming "hordes of minorities" to their countries, Elon Musk took a quick trip to Poland. The billionaire chief of SpaceX, Tesla, and X laid a wreath at Auschwitz and then preceded on to a symposium in Krakow, where he told the conservative commentator Ben Shapiro that social media could have averted the Holocaust and bragged that he considered himself "aspirationally Jewish." The tweet, he explained in a different interview, at a different symposium "might be literally the worst and dumbest post I've ever done." But he did not take it down, nor has he moderated his views. If anything his descent into the online fever swamp has only accelerated.

Peloton had a great pandemic. It's a weird thing to say, but the company's premium exercise equipment (expanding from bikes to treadmills and even weight-training tech) were the hot workout-from-home products. That boom made some people (not normal, sensible people) suggest we were never going back to bricks-and-mortar gyms once the world reopened. Now, Peloton's latest financial numbers and statements are not great, and further cuts, nips and tucks are now on the cards. Its shares have gone from 156 in 2021 to less than 3 today.

Spurred by recent advances in Large Language Models (LLMs), virtual assistants are poised to take a leap forward in terms of their dialogue capabilities. Yet a major bottleneck to achieving genuinely transformative task-oriented dialogue capabilities remains the scarcity of high quality data. Existing datasets, while impressive in scale, have limited domain coverage and contain few genuinely challenging conversational phenomena; those which are present are typically unlabelled, making it difficult to assess the strengths and weaknesses of models without time-consuming and costly human evaluation. Moreover, creating high quality dialogue data has until now required considerable human input, limiting both the scale of these datasets and the ability to rapidly bootstrap data for a new target domain. We aim to overcome these issues with LUCID, a modularised and highly automated LLM-driven data generation system that produces realistic, diverse and challenging dialogues. We use LUCID to generate a seed dataset of 4,277 conversations across 100 intents to demonstrate its capabilities, with a human review finding consistently high quality labels in the generated data.

The negative consequence of this openness of social media platforms is the spread of false information disguised as truth, i.e., fake news. Fake news can be defined as deceptive posts with an intention to mislead consumers in their purchase or approaching the context of misinformation and disinformation (Xiao et al, 2020). Specifically, while misinformation is an inadvertent action, disinformation is a deliberate creation/sharing of false information. The authenticity and intention can be distinguished as: (i) non-factual and mislead, i.e., deceptive news and disinformation; (ii) factual and mislead (cherry-picking); (iii) undefined and mislead (click-bait); and (iv) non-factual and undefined, i.e., misinformation. Misinformation and fake news are characterized by their big volume, uncertainty, and short-lived nature. Furthermore, they disseminate faster and further on social media sites causing serious impact on politics and economics (Tandoc, 2019). Accordingly, the report on digital transformation of media and the rise of disinformation/fake news of the European Union (EU) (Martens et al, 2018) reinforces the need to strengthen trust in digital media.

Currently, the foundation models represented by large language models have made dramatic progress and are used in a very wide range of domains including 2D and 3D vision. As one of the important application domains of foundation models, earth observation has attracted attention and various approaches have been developed. When considering earth observation as a single image capture, earth observation imagery can be processed as an image with three or more channels, and when it comes with multiple image captures of different timestamps at one location, the temporal observation can be considered as a set of continuous image resembling video frames or medical SCAN slices. This paper presents Spatio-Temporal SwinMAE (ST-SwinMAE), an architecture which particularly focuses on representation learning for spatio-temporal image processing. Specifically, it uses a hierarchical Masked Auto-encoder (MAE) with Video Swin Transformer blocks. With the architecture, we present a pretrained model named Degas 100M as a geospatial foundation model. Also, we propose an approach for transfer learning with Degas 100M, which both pretrained encoder and decoder of MAE are utilized with skip connections added between them to achieve multi-scale information communication, forms an architecture named Spatio-Temporal SwinUNet (ST-SwinUNet). Our approach shows significant improvements of performance over existing state-of-the-art of foundation models. Specifically, for transfer learning of the land cover downstream task on the PhilEO Bench dataset, it shows 10.4\% higher accuracy compared with other geospatial foundation models on average.