Goto

Collaborating Authors

 Industry


Cultural Prompting Improves the Empathy and Cultural Responsiveness of GPT-Generated Therapy Responses

arXiv.org Artificial Intelligence

Large Language Model (LLM)-based conversational agents offer promising solutions for mental health support, but lack cultural responsiveness for diverse populations. This study evaluated the effectiveness of cultural prompting in improving cultural responsiveness and perceived empathy of LLM-generated therapeutic responses for Chinese American family caregivers. Using a randomized controlled experiment, we compared GPT-4o and Deepseek-V3 responses with and without cultural prompting. Thirty-six participants evaluated input-response pairs on cultural responsiveness (competence and relevance) and perceived empathy. Results showed that cultural prompting significantly enhanced GPT-4o's performance across all dimensions, with GPT-4o with cultural prompting being the most preferred, while improvements in DeepSeek-V3 responses were not significant. Mediation analysis revealed that cultural prompting improved empathy through improving cultural responsiveness. This study demonstrated that prompt-based techniques can effectively enhance the cultural responsiveness of LLM-generated therapeutic responses, highlighting the importance of cultural responsiveness in delivering empathetic AI-based therapeutic interventions to culturally and linguistically diverse populations.


Use of Retrieval-Augmented Large Language Model Agent for Long-Form COVID-19 Fact-Checking

arXiv.org Artificial Intelligence

The COVID-19 infodemic calls for scalable fact-checking solutions that handle long-form misinformation with accuracy and reliability. This study presents SAFE (system for accurate fact extraction and evaluation), an agent system that combines large language models with retrieval-augmented generation (RAG) to improve automated fact-checking of long-form COVID-19 misinformation. SAFE includes two agents - one for claim extraction and another for claim verification using LOTR-RAG, which leverages a 130,000-document COVID-19 research corpus. An enhanced variant, SAFE (LOTR-RAG + SRAG), incorporates Self-RAG to refine retrieval via query rewriting. We evaluated both systems on 50 fake news articles (2-17 pages) containing 246 annotated claims (M = 4.922, SD = 3.186), labeled as true (14.1%), partly true (14.4%), false (27.0%), partly false (2.2%), and misleading (21.0%) by public health professionals. SAFE systems significantly outperformed baseline LLMs in all metrics (p < 0.001). For consistency (0-1 scale), SAFE (LOTR-RAG) scored 0.629, exceeding both SAFE (+SRAG) (0.577) and the baseline (0.279). In subjective evaluations (0-4 Likert scale), SAFE (LOTR-RAG) also achieved the highest average ratings in usefulness (3.640), clearness (3.800), and authenticity (3.526). Adding SRAG slightly reduced overall performance, except for a minor gain in clearness. SAFE demonstrates robust improvements in long-form COVID-19 fact-checking by addressing LLM limitations in consistency and explainability. The core LOTR-RAG design proved more effective than its SRAG-augmented variant, offering a strong foundation for scalable misinformation mitigation.


DREAMer-VXS: A Latent World Model for Sample-Efficient AGV Exploration in Stochastic, Unobserved Environments

arXiv.org Artificial Intelligence

The paradigm of learning-based robotics holds immense promise, yet its translation to real-world applications is critically hindered by the sample inefficiency and brittleness of conventional model-free reinforcement learning algorithms. In this work, we address these challenges by introducing DREAMer-VXS, a model-based framework for Autonomous Ground Vehicle (AGV) exploration that learns to plan from imagined latent trajectories. Our approach centers on learning a comprehensive world model from partial and high-dimensional LiDAR observations. This world model is composed of a Convolutional Variational Autoencoder (VAE), which learns a compact representation of the environment's structure, and a Recurrent State-Space Model (RSSM), which models complex temporal dynamics. By leveraging this learned model as a high-speed simulator, the agent can train its navigation policy almost entirely in imagination. This methodology decouples policy learning from real-world interaction, culminating in a 90% reduction in required environmental interactions to achieve expert-level performance when compared to state-of-the-art model-free SAC baselines. The agent's behavior is guided by an actor-critic policy optimized with a composite reward function that balances task objectives with an intrinsic curiosity bonus, promoting systematic exploration of unknown spaces. We demonstrate through extensive simulated experiments that DREAMer-VXS not only learns orders of magnitude faster but also develops more generalizable and robust policies, achieving a 45% increase in exploration efficiency in unseen environments and superior resilience to dynamic obstacles.


Instagram's age-verification identified a moustachioed adult as over 16 โ€“ but how did it go with a 13-year-old?

The Guardian

In November Meta began notifying under-16 Instagram and Facebook users their accounts will be deactivated as part of Australia's social media ban for children. In November Meta began notifying under-16 Instagram and Facebook users their accounts will be deactivated as part of Australia's social media ban for children. Instagram's age-verification identified a moustachioed adult as over 16 - but how did it go with a 13-year-old? Meta platform allows users under 16 in Australia to change their date of birth - but only after clearing a'video selfie' or providing government ID Instagram's process for determining whether a user is over 16 is relatively quick and painless if you're clearly an adult - but how does it work if a 13-year-old tries to change their account's date of birth to make them appear grown up? Meta in November began notifying Instagram and Facebook users whose date of birth is set as under 16 - or who the platform understands to be under 16 - that their accounts will be deactivated as part of Australia's social media ban for children.


UK under 'spy in the sky' surveillance as hundreds of drones deployed across nation

FOX News

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by Refinitiv Lipper .


Netflix quietly makes major change to platform with no warning as fans rage over 'customer hostile' policy

Daily Mail - Science & tech

Trump's R-word slur against Tim Walz costs a crucial GOP vote that could tip DC balance of power Brian Walshe shares jaw-dropping explanation of how his wife'died' and why he chopped up her body Hollywood golden couple with 18 year age-gap spotted during rare outing... can you guess who these stars are? Real estate experts sound alarm over toxic mortgage trap and wave of demolitions across America: Heading to'extinction' Mystery of Nikki Haley's son EXPOSED: Nepo baby explodes on to the scene as America First patriot. But here's what his mother really thinks... Trump's MRI scan results released by White House Mom who spent 10 years'gentle parenting' admits it was a mistake: 'My kids are anxious, insecure and entitled' Is this the END of Ozempic? Ellie Goulding, 38, and Sienna Miller, 43, are pregnant! Nashville neighbors can see what's REALLY going on with Nicole Kidman.


Hillsborough police report 'may not give answers'

BBC News

Hillsborough police report'may not give answers' Families of some of those killed in the Hillsborough disaster fear they may once again be denied full accountability as the long-delayed report into police conduct surrounding the stadium crush is due to be published on Tuesday. Several people who worked on the Independent Office for Police Conduct (IOPC) investigation - including a former director - have told the BBC they doubt the report will deliver all the answers survivors and bereaved relatives were promised. Some have warned that it may lead to accusations of another Hillsborough cover-up. Families have also criticised the length and cost of the investigation - the largest of its kind ever carried out in England and Wales. The police watchdog has spent more than 13 years examining the actions of South Yorkshire Police and other forces in the aftermath of the 1989 disaster in which 97 Liverpool supporters were killed during an FA Cup semi-final at Sheffield Wednesday's Hillsborough ground.


The 110 very best Cyber Monday deals in the US, curated and vetted

The Guardian

These are products we believe are worth purchasing year-round - the discount is just a bonus. These are products we believe are worth purchasing year-round - the discount is just a bonus. Our experts found the best deals and sales that are actually worth your money. The Guardian's journalism is independent. We will earn a commission if you buy something through an affiliate link. The Guardian's journalism is independent. We will earn a commission if you buy something through an affiliate link. We all have holiday traditions we look forward to each year: cooking your grandmother's classic stuffing recipe. With the influx of these so-called "doorbuster deals", it can be hard to know a true steal from a modest markdown. So we've asked shopping experts to curate the best Black Friday and Cyber Monday sales across five of the most-shopped for categories. Whether you're looking for a much-needed sleep upgrade or a cordless vacuum that'll stand the test of time, below is our list of the best Cyber Monday deals across streaming, home, kitchen, tech, travel and wellness products. These are items that normally add up fast but right now are going for prices you won't wince at. To put together our list of deals, we enlisted the help of Guardian contributors with years of experience testing products ranging from blenders to vacuums. Our recommendations are based on items tested and loved by our contributors and staff.


The darkest fabric ever made is now a dress

Popular Science

A bird's ultrablack feathers inspired this versatile material. Breakthroughs, discoveries, and DIY tips sent every weekday. There is black, and then there is The shade defined as a black that reflects less than 0.5 percent of the light that hits it, is used on everything from telescopes to cameras. This uniquely dark color is not easy to produce and may appear less black when it is viewed at an angle. To find a better way to reproduce this cool color, a team at Cornell University looked to nature.


Sutton's predictions v Tailenders host Felix White

BBC News

Aston Villa are going for a fourth successive Premier League victory when they travel to Brighton on Wednesday, but should Unai Emery's side change the way they have been scoring goals on their winning run? There is apparently some debate about whether Villa's xG (expected goals) is unsustainable because they are scoring from long range, but that's nonsense, said BBC Sport football expert Chris Sutton. Villa have good players who can shoot from the edge of the box, so are you seriously going to tell them not to shoot now, because of xG? Give me a break. Sutton is making predictions for all 380 Premier League games this season, against AI, BBC Sport readers and a variety of guests. For the midweek fixtures in week 14, he takes on musician, author and Fulham fan Felix White. White is the guitarist with The Maccabees and 86TVs. His new book'Whatever will be, will be: A Matter of Life and Football' is out now.