Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection. To overcome this issue, we propose a novel framework that leverages a small language model (SLM) classifier for initial detection, followed by a LLM as constrained reasoner to generate detailed explanations for detected hallucinated content. This study optimizes the real-time interpretable hallucination detection by introducing effective prompting techniques that align LLM-generated explanations with SLM decisions. Empirical experiment results demonstrate its effectiveness, thereby enhancing the overall user experience.

Recent developments in recommendation have harnessed the collaborative power of graph neural networks (GNNs) in learning users' preferences from user-item networks. Despite emerging regulations addressing fairness of automated systems, unfairness issues in graph collaborative filtering remain underexplored, especially from the consumer's perspective. Despite numerous contributions on consumer unfairness, only a few of these works have delved into GNNs. A notable gap exists in the formalization of the latest mitigation algorithms, as well as in their effectiveness and reliability on cutting-edge models. This paper serves as a solid response to recent research highlighting unfairness issues in graph collaborative filtering by reproducing one of the latest mitigation methods. The reproduced technique adjusts the system fairness level by learning a fair graph augmentation. Under an experimental setup based on 11 GNNs, 5 non-GNN models, and 5 real-world networks across diverse domains, our investigation reveals that fair graph augmentation is consistently effective on high-utility models and large datasets. Experiments on the transferability of the fair augmented graph open new issues for future recommendation studies. Source code: https://github.com/jackmedda/FA4GCF.

Large language models (LLMs) are aligned with human preferences by reinforcement learning from human feedback (RLHF). Effective data sampling is crucial for RLHF, as it determines the efficiency of model training, ensuring that models learn from the informative samples. To achieve better data generation, we propose a new sampling method called Preference-Guided Reflective Sampling (PRS). PRS frames the response generation as an optimization process to the explicitly specified user preference described in natural language. It employs a tree-based generation framework to enable an efficient sampling process, which guides the direction of generation through preference and better explores the sampling space with adaptive self-refinement. Notably, PRS can align LLMs to diverse preferences. We study preference-controlled text generation for instruction following and keyword-focused document summarization. Our findings indicate that PRS, across different LLM policies, generates training data with much higher rewards than strong baselines. PRS also excels in post-RL training.

Most music widely consumed in Western Countries contains song lyrics, with U.S. samples reporting almost all of their song libraries contain lyrics. In parallel, social science theory suggests that personal values - the abstract goals that guide our decisions and behaviors - play an important role in communication: we share what is important to us to coordinate efforts, solve problems and meet challenges. Thus, the values communicated in song lyrics may be similar or different to those of the listener, and by extension affect the listener's reaction to the song. This suggests that working towards automated estimation of values in lyrics may assist in downstream MIR tasks, in particular, personalization. However, as highly subjective text, song lyrics present a challenge in terms of sampling songs to be annotated, annotation methods, and in choosing a method for aggregation. In this project, we take a perspectivist approach, guided by social science theory, to gathering annotations, estimating their quality, and aggregating them. We then compare aggregated ratings to estimates based on pre-trained sentence/word embedding models by employing a validated value dictionary. We discuss conceptually 'fuzzy' solutions to sampling and annotation challenges, promising initial results in annotation quality and in automated estimations, and future directions.

California lawmakers intend to shelve legislation that would have required Google to pay news outlets for distributing their content, and in its place announced a new public-private partnership between the state and the tech giant that will fund programs to research artificial intelligence and bolster local journalism. The plan lays out a commitment of nearly 250 million over the next five years, with one-fourth of the money coming from state taxpayers and three-fourths of it coming from Google and possibly other private donors. The money will go toward two new initiatives administered by UC Berkeley's Graduate School of Journalism: a fund to distribute millions of dollars to California news outlets, and an "AI accelerator" to develop ways for journalists to use the powerful technology. "This agreement represents a major breakthrough in ensuring the survival of newsrooms and bolstering local journalism across California -- leveraging substantial tech industry resources without imposing new taxes on Californians," Gov. Gavin Newsom said in a statement. "The deal not only provides funding to support hundreds of new journalists, but helps rebuild a robust and dynamic California press corps for years to come, reinforcing the vital role of journalism in our democracy."

Will.i.am has been embracing innovative technology for years. Now he is using artificial intelligence in an effort to transform how we listen to the radio. The musician, entrepreneur and tech investor has launched RAiDiO.FYI, a set of interactive radio stations themed around topics like sport, pop culture, and politics. Each station is fundamentally interactive: tune in and you'll be welcomed by name by an AI host "live from the ether," the Black Eyed Peas frontman tells TIME. Hosts talk about their given topic before playing some music.

This year, Google decided not only to update the design of its Pixel phones but also put its AI features front and center. The Pixel 9 Pro and 9 Pro XL are the first Pixels that have swapped the Assistant for Gemini. With its latest flagships, Google continues to improve its cameras, by upgrading its primary sensor and expanding its suite of editing tools. And to power all those new AI tricks, the company has equipped the devices with its newest Tensor processor, designed to handle on-device Gemini tasks. For the first time, too, the Pro-branded Pixel is available in two sizes, with a smaller version joining the family. Better yet, if you go for the Pixel 9 Pro, you'll be getting a largely identical phone to the pricier 6.8-inch Pixel 9 Pro XL. Please note: no camera compromise here, Apple.

Every family and friendship group has that one person who is always the designated photographer. If that's you, you'll be happy to hear that the days of missing out on being in group photos are finally a thing of the past. Google's Pixel 9 smartphones go on sale this week, and there's one new tool that people can't wait to try - Add Me. As the name suggests, Add Me allows photographers to add themselves into group snaps, using artificial intelligence (AI). Ahead of its release tomorrow, Google sent MailOnline's Shivali Best the Google Pixel 9 Pro XL so she could try Add Me for herself - with hilarious results.

Rotten Tomatoes just added a new "Verified Hot" badge that indicates an overall positive user score that will join the "Certified Fresh" badge for critic scores. To qualify for this designation, a movie or show needs to have a Verified Audience Score of 90 percent or higher. Finally, the dregs will be slapped with a "Stale" badge, which is for any show or movie that falls beneath 60 percent. Rotten Tomatoes is trying to get around review bombing here by mandating that user reviews be from people who actually saw the movie in question. There are a couple of little problems with this. It verifies that a consumer saw the movie via the ticketing firm Fandango, and there are plenty of other ticketing firms out there, including, you know, the theater cashier.

Fox News chief political anchor Bret Baier has the latest on the pros and cons of the bombshell developments on'Special Report.' TOP OF THE CHARTS: The U.S. topped another study that looked at the fastest-developing artificial intelligence industries in the world, according to a new report. AI ON THE BALLOT: A librarian running as a nonpartisan candidate for mayor of Cheyenne, Wyoming, promises to allow an artificial intelligence bot created by OpenAI to govern the state's capital city. AI POWER PLAY: Google has its eye on the prize -- artificial intelligence -- and it's making a bold power play in the tech arena. The company's recent Made by Google event was more than just showcasing new technology.