This paper presents the first few-shot LLM-based chatbot that almost never hallucinates and has high conversationality and low latency. WikiChat is grounded on the English Wikipedia, the largest curated free-text corpus. WikiChat generates a response from an LLM, retains only the grounded facts, and combines them with additional information it retrieves from the corpus to form factual and engaging responses. We distill WikiChat based on GPT-4 into a 7B-parameter LLaMA model with minimal loss of quality, to significantly improve its latency, cost and privacy, and facilitate research and deployment. Using a novel hybrid human-and-LLM evaluation methodology, we show that our best system achieves 97.3% factual accuracy in simulated conversations. It significantly outperforms all retrieval-based and LLM-based baselines, and by 3.9%, 38.6% and 51.0% on head, tail and recent knowledge compared to GPT-4. Compared to previous state-of-the-art retrieval-based chatbots, WikiChat is also significantly more informative and engaging, just like an LLM. WikiChat achieves 97.9% factual accuracy in conversations with human users about recent topics, 55.0% better than GPT-4, while receiving significantly higher user ratings and more favorable comments.

We address an important gap in detecting political bias in news articles. Previous works that perform document classification can be influenced by the writing style of each news outlet, leading to overfitting and limited generalizability. Our approach overcomes this limitation by considering both the sentence-level semantics and the document-level rhetorical structure, resulting in a more robust and style-agnostic approach to detecting political bias in news articles. We introduce a novel multi-head hierarchical attention model that effectively encodes the structure of long documents through a diverse ensemble of attention heads. While journalism follows a formalized rhetorical structure, the writing style may vary by news outlet. We demonstrate that our method overcomes this domain dependency and outperforms previous approaches for robustness and accuracy. Further analysis and human evaluation demonstrate the ability of our model to capture common discourse structures in journalism. Our code is available at: https://github.com/xfactlab/emnlp2023-Document-Hierarchy

The remaining Beatles, Paul McCartney and Ringo Starr, have completed the band's final song, decades after their breakup and the deaths of John Lennon and George Harrison. The band announced the song, titled "Now and Then," will be available worldwide Thursday, Nov. 2, paired with a re-release of their very first single, "Love Me Do," which debuted in 1962. "Now and Then" features vocals from Lennon as well as guitar performed by Harrison, recorded six years before his 2001 death. According to a press release for the song, Lennon recorded a demo with vocals and piano in the late 1970s while living in the Dakota building in New York. The Beatles announced a new song, "Now and Then," featuring contributions from the departed members of the band, John Lennon and George Harrison.

CyberGuy explains a new grill powered by AI that can cook a burger in under a minute. Have you ever wondered what it would be like to have a robot cook your burger for you? Well, you might not have to wait too long to find out. A robotic startup called Aniai has developed a revolutionary device that can cook eight juicy burgers in less than a minute, or up to 200 patties an hour. It's called the Alpha Grill, and it's not your ordinary burger-flipping robot.

There are five nights to be survived at cursed old pizza spot Freddy Fazbear's yet it feels like an awful lot more in this surprisingly flat attempt to turn a hit video game into a hit movie. At a flabby, sign-of-the-times 110 minutes, there's far too much of so many things – dream sequences, exposition, first act buildup – and far too little of what one would naturally expect from something as surface-level silly as this – fun. It's partly because writer-director Emma Tammi and game creator Scott Cawthon, acting as co-writer here, seem frighteningly unsure of how seriously they're supposed to take Five Nights at Freddy's and so we're left equally confused. It clangs from straight-faced speeches about childhood trauma to cartoonish kids' movie-level goofiness, tonally awkward and strangely, maddeningly dull, unravelling a mystery that's as predictable as it is uninteresting. Five Nights at Freddy's tells of a dilapidated Chuck E Cheese-esque pizza restaurant for kids, greasy slices soundtracked by a performing band of robotic mascots.

Heck, even reputable tech companies are selling us solutions to reimagine historical events. The venerated camera company officially announced the hotly-anticipated M11-P on Thursday, its first camera to incorporate the Content Credential secure metadata system. Content Credentials are the result of efforts by the Content Authenticity Initiative (CAI), "a group of creators, technologists, journalists, and activists leading the global effort to address digital misinformation and content authenticity," and the Coalition for Content Provenance and Authenticity (C2PA), "a formal coalition dedicated exclusively to drafting technical standards and specifications as a foundation for universal content provenance." These intertwined industry advocacy groups created Content Credentials system in response to growing abuse and misuse of generative AI systems in creating and spreading misinformation online. "The Leica M11-P launch will advance the CAI's goal of empowering photographers everywhere to attach Content Credentials to their photographs at the time of capture," Santiago Lyon, Head of Advocacy and Education at CAI, said in a press statement, "creating a chain of authenticity from camera to cloud and enabling photographers to maintain a degree of control over their art, story and context."

Spotify's royalty model will get a massive revamp next year to give "working artists" a bigger cut, according to Music Business Worldwide. Starting in the first quarter of 2024, Spotify will reportedly implement three changes meant to "combat three drains on the royalty pool." The first one is establishing a minimum number of annual streams a track must reach before it starts generating royalties, which is supposed to demonetize tracks that earn less than 5 cents a month. Apparently, while these tracks make up a tiny percentage of music on the platform -- 99.5 percent of all monetized content will still be earning money after this change -- their royalties still cost Spotify tens of millions of dollars a year. Based on Music Business Worldwide's computations, a track has to generate 200 plays a year to be able to earn 5 cents.

With advancements in natural language processing (NLP) models, automatic explanation generation has been proposed to mitigate misinformation on social media platforms in addition to adding warning labels to identified fake news. While many researchers have focused on generating good explanations, how these explanations can really help humans combat fake news is under-explored. In this study, we compare the effectiveness of a warning label and the state-of-the-art counterfactual explanations generated by GPT-4 in debunking misinformation. In a two-wave, online human-subject study, participants (N = 215) were randomly assigned to a control group in which false contents are shown without any intervention, a warning tag group in which the false claims were labeled, or an explanation group in which the false contents were accompanied by GPT-4 generated explanations. Our results show that both interventions significantly decrease participants' self-reported belief in fake claims in an equivalent manner for the short-term and long-term. We discuss the implications of our findings and directions for future NLP-based misinformation debunking strategies.

Generative Artificial Intelligence (AI) is a cutting-edge technology capable of producing text, images, and various media content leveraging generative models and user prompts. Between 2022 and 2023, generative AI surged in popularity with a plethora of applications spanning from AI-powered movies to chatbots. In this paper, we delve into the potential of generative AI within the realm of the World Wide Web, specifically focusing on image generation. Web developers already harness generative AI to help crafting text and images, while Web browsers might use it in the future to locally generate images for tasks like repairing broken webpages, conserving bandwidth, and enhancing privacy. To explore this research area, we have developed WebDiffusion, a tool that allows to simulate a Web powered by stable diffusion, a popular text-to-image model, from both a client and server perspective. WebDiffusion further supports crowdsourcing of user opinions, which we use to evaluate the quality and accuracy of 409 AI-generated images sourced from 60 webpages. Our findings suggest that generative AI is already capable of producing pertinent and high-quality Web images, even without requiring Web designers to manually input prompts, just by leveraging contextual information available within the webpages. However, we acknowledge that direct in-browser image generation remains a challenge, as only highly powerful GPUs, such as the A40 and A100, can (partially) compete with classic image downloads. Nevertheless, this approach could be valuable for a subset of the images, for example when fixing broken webpages or handling highly private content.

This paper presents Nabra, a corpora of Syrian Arabic dialects with morphological annotations. A team of Syrian natives collected more than 6K sentences containing about 60K words from several sources including social media posts, scripts of movies and series, lyrics of songs and local proverbs to build Nabra. Nabra covers several local Syrian dialects including those of Aleppo, Damascus, Deir-ezzur, Hama, Homs, Huran, Latakia, Mardin, Raqqah, and Suwayda. A team of nine annotators annotated the 60K tokens with full morphological annotations across sentence contexts. We trained the annotators to follow methodological annotation guidelines to ensure unique morpheme annotations, and normalized the annotations. F1 and kappa agreement scores ranged between 74% and 98% across features, showing the excellent quality of Nabra annotations. Our corpora are open-source and publicly available as part of the Currasat portal https://sina.birzeit.edu/currasat.