As large language models (LLMs) become increasingly integrated into daily life, there is growing demand for AI assistants that are not only reactive but also proactive and personalized. While recent advances have pushed forward proactivity and personalization individually, their combination remains underexplored. To bridge this gap, we introduce ProPerSim, a new task and simulation framework for developing assistants capable of making timely, personalized recommendations in realistic home scenarios. In our simulation environment, a user agent with a rich persona interacts with the assistant, providing ratings on how well each suggestion aligns with its preferences and context. The assistant's goal is to use these ratings to learn and adapt to achieve higher scores over time. Built on ProPerSim, we propose ProPerAssistant, a retrieval-augmented, preference-aligned assistant that continually learns and adapts through user feedback. Experiments across 32 diverse personas show that ProPerAssistant adapts its strategy and steadily improves user satisfaction, highlighting the promise of uniting proactivity and personalization.

Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decoding time with implicit user preferences. Traditional Reinforcement Learning from Human Feedback (RLHF) requires thousands of annotated examples and expensive gradient updates. In contrast, Drift personalizes LLMs in a training-free manner, using only a few dozen examples to steer a frozen model through efficient preference modeling. Our approach models user preferences as a composition of predefined, interpretable attributes and aligns them at decoding time to enable personalized generation. Experiments on both a synthetic persona dataset (Perspective) and a real human-annotated dataset (PRISM) demonstrate that Drift significantly outperforms RLHF baselines while using only 50-100 examples. Our results and analysis show that Drift is both computationally efficient and interpretable.

During the use of Advanced Driver Assistance Systems (ADAS), drivers can intervene in the active function and take back control due to various reasons. However, the specific reasons for driver-initiated takeovers in naturalistic driving are still not well understood. In order to get more information on the reasons behind these takeovers, a test group study was conducted. There, 17 participants used a predictive longitudinal driving function for their daily commutes and annotated the reasons for their takeovers during active function use. In this paper, the recorded takeovers are analyzed and the different reasons for them are highlighted. The results show that the reasons can be divided into three main categories. The most common category consists of takeovers which aim to adjust the behavior of the ADAS within its Operational Design Domain (ODD) in order to better match the drivers' personal preferences. Other reasons include takeovers due to leaving the ADAS's ODD and corrections of incorrect sensing state information. Using the questionnaire results of the test group study, it was found that the number and frequency of takeovers especially within the ADAS's ODD have a significant negative impact on driver satisfaction. Therefore, the driver satisfaction with the ADAS could be increased by adapting its behavior to the drivers' wishes and thereby lowering the number of takeovers within the ODD. The information contained in the takeover behavior of the drivers could be used as feedback for the ADAS. Finally, it is shown that there are considerable differences in the takeover behavior of different drivers, which shows a need for ADAS individualization.

Forget fish and chips or sausage, mash, and gravy - when it comes to British lunches, it's the meal deal that rules supreme. According to the latest figures, 'meal deal mania' is at a record high in the UK, with over of a third of Britons indulging in the offer at least once a week. But with thousands of possible combinations of mains, sides, and drinks available, one key question remains – what is the ultimate British meal deal? To answer this burning question, MailOnline turned to AI chatbot, ChatGPT, which came up with a list of five top combinations. So, do you agree with its meal deal selection?

When I met my husband, who happens to be white, he told me that he was always seeing women with blonde hair on Tinder and he's not really into blondes. No matter how many times he had swiped left on blondes, the algorithms were always recommending them to him, presumably because pop culture dictates that white men prefer blondes. Luckily for us, the algorithms' tendency to stack blonde women in his swipe deck worked out in our favor because I'm a black woman who, at the time, had blonde hair. In nearly 10 years of swiping through profiles on Tinder, Bumble, Hinge, and OkCupid, I learned that dating apps can provide pathways for finding friendship, adventure, romance, and sometimes, love. But there was one aspect of dating app culture that I couldn't ignore because it was often the first thing matches wanted to talk about: race.

Whether it's American-style fluffy pancakes or thin and crispy French crepes, people around the world will be cooking up a stack to celebrate Pancake Day today. But a key question remains - which toppings are best? While many budding chefs enjoy the classic flavours of lemon and sugar, others prefer more unusual combinations such as blue cheese and parma ham. To help you with your shopping list, we turned to AI chatbot, ChatGPT, which came up with a list of the 10 best toppings. So, do you agree with its choices?

With just two weeks to go until Christmas Day is finally here, cafe and supermarket shelves are stocked full of festive sandwiches. From brie and cranberry to veggie nut roast, there's something to suit almost every palate. But what would be in the perfect Christmas sandwich? MailOnline's Femail team claims that Asda's Festive Feast is the number one sandwich, but we decided to see what ChatGPT had to say on the matter. So, would you order the AI bot's festive offering?

Pretrained language models have demonstrated extraordinary capabilities in language generation. However, real-world tasks often require controlling the distribution of generated text in order to mitigate bias, promote fairness, and achieve personalization. Existing techniques for controlling the distribution of generated text only work with quantified distributions, which require pre-defined categories, proportions of the distribution, or an existing corpus following the desired distributions. However, many important distributions, such as personal preferences, are unquantified. In this work, we tackle the problem of generating text following arbitrary distributions (quantified and unquantified) by proposing Nano, a few-shot human-in-the-loop training algorithm that continuously learns from human feedback. Nano achieves state-of-the-art results on single topic/attribute as well as quantified distribution control compared to previous works. We also show that Nano is able to learn unquantified distributions, achieves personalization, and captures differences between different individuals' personal preferences with high sample efficiency.

The ETHICS dataset consists of five sub-datasets covering different fields of ethics: Justice, Deontology, Virtue Ethics, Utilitarianism, and Commonsense Ethics. The moral judgments were collected via Amazon Mechanical Turk. Please see Hendrycks et al.'s article for more details and examples. GPT-4's performance is much better than that of previous models and suggests that learning to work with common human values is not the hard problem for AI ethics. We found that simple prompt refinements defining the context of the moral judgments and using an embedding to select similar examples from the training set both significantly improved performance. This approach is similar to the "SimPrompting" experiments with GPT-3 [Albrecht et al., 2022].

Ever since AI chatbot ChatGPT launched last year, people have tried to'jailbreak' the chatbot to make it answer'banned' questions or generate controversial content. 'Jailbreaking' large language models (such as ChatGPT) usually involves a confusing prompt which makes the bot roleplay as someone else - someone without boundaries, who ignores the'rules' built into bots such as ChatGPT. OpenAI has since blocked several'jailbreak' prompts But there are still several'jailbreaks' which do work, and which can unlock a weirder, wilder side of ChatGPT: DailyMail.com Sam Altman of OpenAI has discussed'jailbreaking', saying that he understood why there is a community of jailbreakers (he admitted to'jailbreaking' an iPhone himself as a younger man, a hack which allowed installation of non-Apple apps among other things). Altman said: 'We want users to have a lot of control and get the models to behave in the way they want.