--From dating to job interviews, making new friends or simply chatting with the cashier at checkout, engaging in small talk is a vital, everyday social skill. For adults with Autism Spectrum Disorder (ASD), small talk can be particularly challenging, yet it is essential for social integration, building relationships, and accessing professional opportunities. In this study, we present our development and evaluation of an in-home autonomous robot system that allows users to practice small talk. Results from the week-long study show that adults with ASD enjoyed the training, made notable progress in initiating conversations and improving eye contact, and viewed the system as a valuable tool for enhancing their conversational skills. Imagine a scene where three coworkers are engaging in small talk at the beginning of their workday. One of them is Alex, who has Autism Spectrum Disorder (ASD), a neu-rodevelopmental condition that often makes it challenging to understand and interpret social cues [2]. Not bad... just trying to power through this Monday. How about you, Alex? A: Monday is okay. Anything exciting happen this weekend? B: Y eah, I finally tried that new restaurant. It was fantas-- A: I watched a movie. C: Glad you liked the restaurant, Ben. It's my kids' favorite spot these days... What movie did you watch, Alex? A: "The Martian." At first glance, this brief example of a typical interaction appears unremarkable. It represents the everyday small talk that occurs regularly in many workplaces. For workers with ASD, however, such apparently "easy" interactions may present a real challenge. In this example, while Alex responds to direct questions, the responses are brief and lack elaboration. Alex's responses provide minimal information rather than actively participating in the flow of the conversation. Additionally, Alex's lack of response to the last prompt may suggest difficulty in extending or sustaining the dialogue. Although workers with ASD are often highly trained and skilled in job-specific tasks, they frequently face challenges with social interactions in the workplace.

To increase social bonding with interlocutors, humans naturally acquire the ability to respond appropriately in a given situation by considering which conversational skill is most suitable for the response - a process we call skill-of-mind. For large language model (LLM)-based conversational agents, planning appropriate conversational skills, as humans do, is challenging due to the complexity of social dialogue, especially in interactive scenarios. To address this, we propose a skill-of-mind-annotated conversation dataset, named Multifaceted Skill-of-Mind, which includes multi-turn and multifaceted conversational skills across various interactive scenarios (e.g., long-term, counseling, task-oriented), grounded in diverse social contexts (e.g., demographics, persona, rules of thumb). This dataset consists of roughly 100K conversations. Using this dataset, we introduce a new family of skill-of-mind-infused LLMs, named Thanos, with model sizes of 1B, 3B, and 8B parameters. With extensive experiments, these models successfully demonstrate the skill-of-mind process and exhibit strong generalizability in inferring multifaceted skills across a variety of domains. Moreover, we show that Thanos significantly enhances the quality of responses generated by LLM-based conversational agents and promotes prosocial behavior in human evaluations.

Facebook AI has built and open-sourced BlenderBot, the largest-ever open-domain chatbot. It outperforms others in terms of engagement and also feels more human, according to human evaluators. The culmination of years of research in conversational AI, this is the first chatbot to blend a diverse set of conversational skills -- including empathy, knowledge, and personality -- together in one system. We achieved this milestone through a new chatbot recipe that includes improved decoding techniques, novel blending of skills, and a model with 9.4 billion parameters, which is 3.6x more than the largest existing system. Today we're releasing the complete model, code, and evaluation set-up, so that other AI researchers will be able to reproduce this work and continue to advance conversational AI research.

Researchers from all over the world contribute to this repository as a prelude to the peer review process for publication in traditional journals. The articles listed below represent a small fraction of all articles appearing on the preprint server. They are listed in no particular order with a link to each paper along with a brief overview. Links to GitHub repos are provided when available. Especially relevant articles are marked with a "thumbs up" icon.

The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in dialog. In this study, we analyze the internal representations learned by neural open-domain dialog systems and evaluate the quality of these representations for learning basic conversational skills. Our results suggest that standard open-domain dialog systems struggle with answering questions, inferring contradiction, and determining the topic of conversation, among other tasks. We also find that the dyadic, turn-taking nature of dialog is not fully leveraged by these models. By exploring these limitations, we highlight the need for additional research into architectures and training methods that can better capture high-level information about dialog.

Facebook AI has built and open-sourced Blender, the largest-ever open-domain chatbot. It outperforms others in terms of engagement and also feels more human, according to human evaluators. The culmination of years of research in conversational AI, this is the first chatbot to blend a diverse set of conversational skills -- including empathy, knowledge, and personality -- together in one system. We achieved this milestone through a new chatbot recipe that includes improved decoding techniques, novel blending of skills, and a model with 9.4 billion parameters, which is 3.6x more than the largest existing system. Today we're releasing the complete model, code, and evaluation set-up, so that other AI researchers will be able to reproduce this work and continue to advance conversational AI research.

The'gamification' of dating apps is damaging singleton's chances of spotting the right match for them, a psychiatrist has warned. Swiping through endless faces on apps like Tinder and Bumble, known as'infinite swipe', The practice has become so addictive that more than one in 10 users swipe for over 14 hours a week, a survey backing up the claims has revealed. Research has found that nearly 30 per cent of dating app users are spending over seven hours per week trying to find a match, and 14 per cent swipe for over 14 hours, encouraged by a phenomena known as'infinite swipe' that sees users swiping through endless faces on the app The rise of dating apps has given rise to a new user phenomenon: the'infinite swipe. Just as other tech platforms such as Facebook and Google have adopted the persuasive design feature of infinite scroll, to engage the user in habit forming experiences, dating apps have leveraged the power of the'infinite swipe'. Users are'nudged" to process the face of a potential match in less than a second, with little or no context on the person's personality.

Microsoft has acquired a natural language AI firm called Semantic Machines to help Cortana and other bots carry on natural conversations, it announced. The tech "uses the power of machine learning to enable users to discover, access and interact with information and services in a much more natural way, and with significantly less effort," wrote Microsoft AI & Research CTO David Ku. What's more, Microsoft will establish a "conversational AI center" in Berkeley to amp up its language tech and "take conversational computing to a new level." Microsoft pointed out that while Siri, Cortana, Google Assistant and Alexa can execute commands, they can't carry on a conversation in any meaningful way (Google's much-debated Duplex conversation aside). Semantic Machines, however, has developed tech that can understand entire chats, not just orders to do this or that. "For rich and effective communication, intelligent assistants need to be able to have a natural dialogue instead of just responding to commands," said Ku. Semantic Machines should be able to help Microsoft with all that via its primary product, the Conversation Engine.

WASHINGTON: A research arm of the US intelligence community just wrapped up a competition to see who could develop the best facial recognition technology. The challenge: identify as many passengers as possible walking on an aircraft boarding ramp. Of all the entries, it was a Chinese start-up company called Yitu Tech that walked away with the US$25,000 prize this month, the highest of three cash awards. The competition was one of many examples cited in a report by a US-based think tank about how China's military might leverage its country's rapid advances in artificial intelligence to modernise its armed forces and, potentially, seek advantages against the United States. "China is no longer in a position of technological inferiority relative to the United States but rather has become a true peer (competitor) that may have the capability to overtake the United States in AI," said the report, written by Elsa Kania at the Center for a New American Security (CNAS) and due to be released on Tuesday.

Free app Duolingo is a great way to learn the basics of a new language, with small daily lessons that gradually increase your skills, with rewards for progressing. Now the service has added a new feature that's a little different from the back-and-forth translation -- text-based chatbots. These are aimed at helping you improve your conversational skills and skills you might use in real life, such as ordering food, visiting a tourist attraction, shopping for clothing or catching a cab. A variety of scenarios will see you learning how to follow a set of directions, or talk with a doctor. According to the Duolingo chatbot Web page, these bots are programmed to react to thousands of different responses.