Many under-resourced languages require high-quality datasets for specific tasks such as offensive language detection, disinformation, or misinformation identification. However, the intricacies of the content may have a detrimental effect on the annotators. The article aims to revisit an approach of pseudo-labeling sensitive data on the example of Ukrainian tweets covering the Russian-Ukrainian war. Nowadays, this acute topic is in the spotlight of various language manipulations that cause numerous disinformation and profanity on social media platforms. The conducted experiment highlights three main stages of data annotation and underlines the main obstacles during machine annotation. Ultimately, we provide a fundamental statistical analysis of the obtained data, evaluation of models used for pseudo-labelling, and set further guidelines on how the scientists can leverage the corpus to execute more advanced research and extend the existing data samples without annotators' engagement.

In-Context Learning (ICL) and Instruction Tuning (IT) are two primary paradigms of adopting Large Language Models (LLMs) to downstream applications. However, they are significantly different. In ICL, a set of demonstrations are provided at inference time but the LLM's parameters are not updated. In IT, a set of demonstrations are used to tune LLM's parameters in training time but no demonstrations are used at inference time. Although a growing body of literature has explored ICL and IT, studies on these topics have largely been conducted in isolation, leading to a disconnect between these two paradigms. In this work, we explore the relationship between ICL and IT by examining how the hidden states of LLMs change in these two paradigms. Through carefully designed experiments conducted with LLaMA-2 (7B and 13B), we find that ICL is implicit IT. In other words, ICL changes an LLM's hidden states as if the demonstrations were used to instructionally tune the model. Furthermore, the convergence between ICL and IT is largely contingent upon several factors related to the provided demonstrations. Overall, this work offers a unique perspective to explore the connection between ICL and IT and sheds light on understanding the behaviors of LLM. In real-world applications, the success of deploying Large Language Models (LLMs) can largely be attributed to the effectiveness of two primary learning paradigms: 1) In-Context Learning (ICL) and 2) Instruction Tuning (IT).

Recommender systems are ubiquitous yet often difficult for users to control, and adjust if recommendation quality is poor. This has motivated conversational recommender systems (CRSs), with control provided through natural language feedback. However, as with most application domains, building robust CRSs requires training data that reflects system usage$\unicode{x2014}$here conversations with user utterances paired with items that cover a wide range of preferences. This has proved challenging to collect scalably using conventional methods. We address the question of whether it can be generated synthetically, building on recent advances in natural language. We evaluate in the setting of item set recommendation, noting the increasing attention to this task motivated by use cases like music, news, and recipe recommendation. We present TalkTheWalk, which synthesizes realistic high-quality conversational data by leveraging domain expertise encoded in widely available curated item collections, generating a sequence of hypothetical yet plausible item sets, then using a language model to produce corresponding user utterances. We generate over one million diverse playlist curation conversations in the music domain, and show these contain consistent utterances with relevant item sets nearly matching the quality of an existing but small human-collected dataset for this task. We demonstrate the utility of the generated synthetic dataset on a conversational item retrieval task and show that it improves over both unsupervised baselines and systems trained on a real dataset.

With the introduction of ChatGPT, the public's perception of AI-generated content (AIGC) has begun to reshape. Artificial intelligence has significantly reduced the barrier to entry for non-professionals in creative endeavors, enhancing the efficiency of content creation. Recent advancements have seen significant improvements in the quality of symbolic music generation, which is enabled by the use of modern generative algorithms to extract patterns implicit in a piece of music based on rule constraints or a musical corpus. Nevertheless, existing literature reviews tend to present a conventional and conservative perspective on future development trajectories, with a notable absence of thorough benchmarking of generative models. This paper provides a survey and analysis of recent intelligent music generation techniques, outlining their respective characteristics and discussing existing methods for evaluation. Additionally, the paper compares the different characteristics of music generation techniques in the East and West as well as analysing the field's development prospects.

Transformer-based language model approaches to automated story generation currently provide state-of-the-art results. However, they still suffer from plot incoherence when generating narratives over time, and critically lack basic commonsense reasoning. Furthermore, existing methods generally focus only on single-character stories, or fail to track characters at all. To improve the coherence of generated narratives and to expand the scope of character-centric narrative generation, we introduce Commonsense-inference Augmented neural StoryTelling (CAST), a framework for introducing commonsense reasoning into the generation process with the option to model the interaction between multiple characters. We find that our CAST method produces significantly more coherent, on-topic, enjoyable and fluent stories than existing models in both the single-character and two-character settings in three storytelling domains.

The living room is where most people spend a good chunk of their time when they want to relax, but most people's home theater setup could use a little TLC. While you can drop serious money fast in this space, that doesn't have to be the case. If you've got a movie-lover on your gift list, or someone who's particularly hard to shop for, getting them something to upgrade their TV-watching experience is usually a set bet. Here are some of the best home theater gifts for this year, and no, not all of them cost a fortune. While the latest Apple TV model isn't a massive leap over its predecessor, there are a few updates that make it worthy of a holiday splurge.

YouTube on Thursday unveiled some new experimental AI services, including a feature called Dream Track in YouTube Shorts. It creates up to 30-second soundtracks using AI-generation versions of artists' voices. Though musicians have mostly pushed back on AI (and their voices being used for training models without permission or compensation), YouTube got nine big names from the music industry to participate, including John Legend, Troye Sivan, CharliXCX and T-Pain. The company hoped to announce the feature at its Made on YouTube event in September, but it's been tied up in negotiations with recording companies over rights and payments. Users can access Dream Track by typing an idea into the creation prompt and choosing from one of the participating artists.

Lachlan Murdoch will become the sole chair of both companies in November. As Rupert Murdoch marked his final day as Executive Chairman of News Corp on Wednesday, the media icon saluted his son Lachlan as the right man to lead the company forward. "Lachlan is a principled leader, and a believer in the social purpose of journalism. I hope to continue an active role in the company," Rupert Murdoch said during the company's annual shareholders meeting. Rupert Murdoch, 92, will now be Chairman Emeritus of FOX Corporation and News Corp; he will mark his final day at the former on Friday.

YouTube has teamed up with music artists including John Legend and Sia to offer AI-generated versions of their singing voices as soundtracks for creator videos. The Google-owned video platform is using a music generation model created by the search company's AI unit to produce the unique 30-second clips in a limited trial. The nine artists are: Alec Benjamin, Charlie Puth, Charli XCX, Demi Lovato, John Legend, Sia, T-Pain, Troye Sivan and Papoose. YouTube said the experiment, called Dream Track, has been opened to a small group of US creators using its Shorts feature – the platform's answer to TikTok. In a blogpost, YouTube said creators would be able to produce a 30-second soundtrack by typing a text prompt.

Ediaf Piaf's rich tones will once again delight music fans as she stars in her own biopic - despite having passed away over 60 years ago. An AI recreation of Piaf's unmistakable voice will be used to narrate'Piaf', an upcoming film about her tumultuous life. Scientists from Warner Music Group have trained an AI on hundreds of recordings of Piaf, some over 80 years old, in order to'revive' Piaf's voice and image. Animation will be used alongside archival footage to tell the story of how Piaf rose to become an icon, including some previously unknown aspects. Julie Veille, who conceived the idea for the film, says that this will'help bring her story into the 21st century.' 'Piaf' will be a 90-minute film about the life of Edith Piaf and will be narrated by an AI reconstruction of the singer's voice The film, 'Piaf', will feature animation as well as archival footage of interviews, performances, and personal footage to tell the story of one of France's most iconic musicians Vielle said: 'It has been the greatest privilege to work alongside Edith's Estate.