Considerable advancements have been made to tackle the misrepresentation of information derived from reference articles in the domains of fact-checking and faithful summarization. However, an unaddressed aspect remains - the identification of social media posts that manipulate information within associated news articles. This task presents a significant challenge, primarily due to the prevalence of personal opinions in such posts. We present a novel task, identifying manipulation of news on social media, which aims to detect manipulation in social media posts and identify manipulated or inserted information. To study this task, we have proposed a data collection schema and curated a dataset called ManiTweet, consisting of 3.6K pairs of tweets and corresponding articles. Our analysis demonstrates that this task is highly challenging, with large language models (LLMs) yielding unsatisfactory performance. Additionally, we have developed a simple yet effective basic model that outperforms LLMs significantly on the ManiTweet dataset. Finally, we have conducted an exploratory analysis of human-written tweets, unveiling intriguing connections between manipulation and the domain and factuality of news articles, as well as revealing that manipulated sentences are more likely to encapsulate the main story or consequences of a news outlet.

Many recent loss functions in deep metric learning are expressed with logarithmic and exponential forms, and they involve margin and scale as essential hyper-parameters. Since each data class has an intrinsic characteristic, several previous works have tried to learn embedding space close to the real distribution by introducing adaptive margins. However, there was no work on adaptive scales at all. We argue that both margin and scale should be adaptively adjustable during the training. In this paper, we propose a method called Adaptive Margin and Scale (AdaMS), where hyper-parameters of margin and scale are replaced with learnable parameters of adaptive margins and adaptive scales for each class. Our method is evaluated on Wall Street Journal dataset, and we achieve outperforming results for word discrimination tasks.

The Image Signal Processor (ISP) is a component of digital cameras capable of performing various tasks to improve image quality, as demosaicing, denoising, and white balance. The set of tasks performed by the ISP is called ISP pipeline, divided in preproccessing and postprocessing steps, and may differ from manufacturer to manufacturer [1]. Nowadays, Machine Learning is used to replace partially or the entire ISP pipeline. Particulary, Deep Learning is employed to replace ISP tasks, working on noise removal or some image feaure that hinders processing over the network. Deep Learning network provides an improvement in relation to computational efficiency and processing time. This survey paper aims to analyze recent studies, 27 research papers, that implemented Deep Learning based ISP pipeline.

Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers. This problem has been extensively studied under the supervised setting, where both answer and rationale annotations are given. Because rationale annotations are expensive to collect and not always available, recent efforts have been devoted to developing methods that do not rely on supervision for rationales. However, such methods have limited capacities in modeling interactions between sentences, let alone reasoning across multiple documents. This work proposes a principled, probabilistic approach for training explainable multi-hop QA systems without rationale supervision. Our approach performs multi-hop reasoning by explicitly modeling rationales as sets, enabling the model to capture interactions between documents and sentences within a document. Experimental results show that our approach is more accurate at selecting rationales than the previous methods, while maintaining similar accuracy in predicting answers.

Large language models (LLMs) exhibit remarkable performance across various NLP tasks. However, they often generate incorrect or hallucinated information, which hinders their practical applicability in real-world scenarios. Human feedback has been shown to effectively enhance the factuality and quality of generated content, addressing some of these limitations. However, this approach is resource-intensive, involving manual input and supervision, which can be time-consuming and expensive. Moreover, it cannot be provided during inference, further limiting its practical utility in dynamic and interactive applications. In this paper, we introduce ReFeed, a novel pipeline designed to enhance LLMs by providing automatic retrieval feedback in a plug-and-play framework without the need for expensive fine-tuning. ReFeed first generates initial outputs, then utilizes a retrieval model to acquire relevant information from large document collections, and finally incorporates the retrieved information into the in-context demonstration for output refinement, thereby addressing the limitations of LLMs in a more efficient and cost-effective manner. Experiments on four knowledge-intensive benchmark datasets demonstrate our proposed ReFeed could improve over +6.0% under zero-shot setting and +2.5% under few-shot setting, compared to baselines without using retrieval feedback.

Recent neural retrieval mainly focuses on ranking short texts and is challenged with long documents. Existing work mainly evaluates either ranking passages or whole documents. However, there are many cases where the users want to find a relevant passage within a long document from a huge corpus, e.g. legal cases, research papers, etc. In this scenario, the passage often provides little document context and thus challenges the current approaches to finding the correct document and returning accurate results. To fill this gap, we propose and name this task Document-Aware Passage Retrieval (DAPR) and build a benchmark including multiple datasets from various domains, covering both DAPR and whole-document retrieval. In experiments, we extend the state-of-the-art neural passage retrievers with document-level context via different approaches including prepending document summary, pooling over passage representations, and hybrid retrieval with BM25. The hybrid-retrieval systems, the overall best, can only improve on the DAPR tasks marginally while significantly improving on the document-retrieval tasks. This motivates further research in developing better retrieval systems for the new task. The code and the data are available at https://github.com/kwang2049/dapr

A suspected AI-generated image claiming to show an explosion near the Pentagon went viral on Twitter Monday, sending markets crashing. Dozens of verified accounts - including national news organizations - reshared what shows black smoke billowing up from the ground next to a white building. The image appears so realistic that people became frantic as it circulated the platform around 10 am ET, which caused the S&P 500 to drop 10 points in five minutes as the image went viral. The Arlington Fire Department swiftly debunked the event, stating that'there is no explosion or incident taking place at or near the Pentagon reservation.' It comes as fears about the power of artificial technology in spreading misinformation, particularly in the build-up to the 2024 Presidential Election.

Kurt "CyberGuy" Knutsson explains whether robot security guards are better or worse for society. A new study is suggesting that robots with more "charismatic" voices – as opposed to flat, matter-of-fact ones – can help people be more creative. Scientists from Denmark found that students who are given a task by a robot with a voice programmed to be more "engaging" and "inspiring" performed better. These students were also more creative than students who received instructions from an identical robot with a flat voice, according to the findings from researchers in Denmark as published by Frontiers in Communication, a peer-reviewed, open-access science journal. Increasingly, social robots are being used for support in educational settings, as SWNS, the British news service, noted.

Square Enix wants a hit Final Fantasy game that's just as popular as any game in the storied history. It's taken seven years to get from the tepidly-received Final Fantasy XV to Final Fantasy XVI, and the company continues to wrestle with what a FF game is in 2023. The company courted nostalgia with FF7 Remake (and the Pixel Remaster series). At the same time, its MMORPG, Final Fantasy XIV, continues to be a huge success – but what about the prestige title? It has a plan, and it involves giant-summoned monster battles with different styles of play, a single controllable protagonist with guest-star allies, a support dog that grows up with you, horny antagonists, wicked moms and several bleak plot twists to help establish the plot and characters relatively early on.

"I think, initially, Ubisoft approached me because of my electronic music background – my live career, my albums, my touring. But I didn't know if I was the right person for the job, you know?" Composer Brendan Angelides has never worked in video game music before. You might know him better as Eskmo or Welder, or perhaps as the mind behind the music of TV shows 13 Reasons Why or Billions. When Ubisoft approached him to be the composer for its sort-of reboot of the Assassin's Creed franchise, Mirage, he had doubts. The game is set at the height of the Islamic golden age, and centres around Baghdad: a hub flowing with the lifeblood of a changing world, a cultural centre of art and science, old and new.