Norm discovery is important for understanding and reasoning about the acceptable behaviors and potential violations in human communication and interactions. We introduce NormSage, a framework for addressing the novel task of conversation-grounded multi-lingual, multi-cultural norm discovery, based on language model prompting and self-verification. NormSAGE leverages the expressiveness and implicit knowledge of the pretrained GPT-3 language model backbone, to elicit knowledge about norms through directed questions representing the norm discovery task and conversation context. It further addresses the risk of language model hallucination with a self-verification mechanism ensuring that the norms discovered are correct and are substantially grounded to their source conversations. Evaluation results show that our approach discovers significantly more relevant and insightful norms for conversations on-the-fly compared to baselines (>10+% in Likert scale rating). The norms discovered from Chinese conversation are also comparable to the norms discovered from English conversation in terms of insightfulness and correctness (<3% difference). In addition, the culture-specific norms are promising quality, allowing for 80% accuracy in culture pair human identification. Finally, our grounding process in norm discovery self-verification can be extended for instantiating the adherence and violation of any norm for a given conversation on-the-fly, with explainability and transparency. NormSAGE achieves an AUC of 95.4% in grounding, with natural language explanation matching human-written quality.

In this paper, we present a novel approach to epistemic planning called planning with perspectives (PWP) that is both more expressive and computationally more efficient than existing state-of-the-art epistemic planning tools. Epistemic planning — planning with knowledge and belief — is essential in many multi-agent and human-agent interaction domains. Most state-of-the-art epistemic planners solve epistemic planning problems by either compiling to propositional classical planning (for example, generating all possible knowledge atoms or compiling epistemic formulae to normal forms); or explicitly encoding Kripke-based semantics. However, these methods become computationally infeasible as problem sizes grow. In this paper, we decompose epistemic planning by delegating reasoning about epistemic formulae to an external solver. We do this by modelling the problem using Functional STRIPS, which is more expressive than standard STRIPS and supports the use of external, black-box functions within action models. Building on recent work that demonstrates the relationship between what an agent ‘sees’ and what it knows, we define the perspective of each agent using an external function, and build a solver for epistemic logic around this. Modellers can customise the perspective function of agents, allowing new epistemic logics to be defined without changing the planner. We ran evaluations on well-known epistemic planning benchmarks to compare an existing state-of-the-art planner, and on new scenarios that demonstrate the expressiveness of the PWP approach. The results show that our PWP planner scales significantly better than the state-of-the-art planner that we compared against, and can express problems more succinctly.

The performance of machine learning based network intrusion detection systems (NIDSs) severely degrades when deployed on a network with significantly different feature distributions from the ones of the training dataset. In various applications, such as computer vision, domain adaptation techniques have been successful in mitigating the gap between the distributions of the training and test data. In the case of network intrusion detection however, the state-of-the-art domain adaptation approaches have had limited success. According to recent studies, as well as our own results, the performance of an NIDS considerably deteriorates when the `unseen' test dataset does not follow the training dataset distribution. In some cases, swapping the train and test datasets makes this even more severe. In order to enhance the generalisibility of machine learning based network intrusion detection systems, we propose to extract domain invariant features using adversarial domain adaptation from multiple network domains, and then apply an unsupervised technique for recognising abnormalities, i.e., intrusions. More specifically, we train a domain adversarial neural network on labelled source domains, extract the domain invariant features, and train a One-Class SVM (OSVM) model to detect anomalies. At test time, we feedforward the unlabeled test data to the feature extractor network to project it into a domain invariant space, and then apply OSVM on the extracted features to achieve our final goal of detecting intrusions. Our extensive experiments on the NIDS benchmark datasets of NFv2-CIC-2018 and NFv2-UNSW-NB15 show that our proposed setup demonstrates superior cross-domain performance in comparison to the previous approaches.

Modeling the ideological perspectives of political actors is an essential task in computational political science with applications in many downstream tasks. Existing approaches are generally limited to textual data and voting records, while they neglect the rich social context and valuable expert knowledge for holistic ideological analysis. In this paper, we propose \textbf{PAR}, a \textbf{P}olitical \textbf{A}ctor \textbf{R}epresentation learning framework that jointly leverages social context and expert knowledge. Specifically, we retrieve and extract factual statements about legislators to leverage social context information. We then construct a heterogeneous information network to incorporate social context and use relational graph neural networks to learn legislator representations. Finally, we train PAR with three objectives to align representation learning with expert knowledge, model ideological stance consistency, and simulate the echo chamber phenomenon. Extensive experiments demonstrate that PAR is better at augmenting political text understanding and successfully advances the state-of-the-art in political perspective detection and roll call vote prediction. Further analysis proves that PAR learns representations that reflect the political reality and provide new insights into political behavior.

Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of training on large amounts of noisy image-text data, without relying on expensive accurate labels used in standard vision unimodal supervised learning. The resulting models showed capabilities of strong text-guided image generation and transfer to downstream tasks, while performing remarkably at zero-shot classification with noteworthy out-of-distribution robustness. Since then, large-scale language-vision models like ALIGN, BASIC, GLIDE, Flamingo and Imagen made further improvements. Studying the training and capabilities of such models requires datasets containing billions of image-text pairs. Until now, no datasets of this size have been made openly available for the broader research community. To address this problem and democratize research on large-scale multi-modal models, we present LAION-5B - a dataset consisting of 5.85 billion CLIP-filtered image-text pairs, of which 2.32B contain English language. We show successful replication and fine-tuning of foundational models like CLIP, GLIDE and Stable Diffusion using the dataset, and discuss further experiments enabled with an openly available dataset of this scale. Additionally we provide several nearest neighbor indices, an improved web-interface for dataset exploration and subset generation, and detection scores for watermark, NSFW, and toxic content detection. Announcement page https://laion.ai/laion-5b-a-new-era-of-open-large-scale-multi-modal-datasets/

The White House Office of Science and Technology Policy (OSTP) recently released a whitepaper called "The Blueprint for an AI Bill of Rights: Making Automated Systems Work for the American People". This framework was released one year after OSTP announced the launch of a process to develop "a bill of rights for an AI-powered world." The foreword in this bill clearly illustrates that the White House understands the imminent threats to society that are posed by AI. "Among the great challenges posed to democracy today is the use of technology, data, and automated systems in ways that threaten the rights of the American public. Too often, these tools are used to limit our opportunities and prevent our access to critical resources or services. These problems are well documented. In America and around the world, systems supposed to help with patient care have proven unsafe, ineffective, or biased. Algorithms used in hiring and credit decisions have been found to reflect and reproduce existing unwanted inequities or embed new harmful bias and discrimination. Unchecked social media data collection has been used to threaten people's opportunities, undermine their privacy, or pervasively track their activity--often without their knowledge or consent."

Children who are unable to go to school need digital learning aids and lots of self-motivation. With AI technology we can support them and their parents as well: The AI Learning Helper teaches elementary school children how to read aloud in English and understand stories. There are many reasons why children do not go to school, from physical and mental disabilities or temporary illness to an active choice on the part of their parents. Home schooling has also become hugely more commonplace as a result of the COVID-19 pandemic. But learning from home is not easy: Children miss participating in lessons with their friends, feel less motivated, and are more easily distracted. That's why our innovation team has developed an approach to mitigate the problem: the AI Learning Helper.

A dish of living brain cells has learned to play the 1970s arcade game Pong. About 800,000 cells linked to a computer gradually learned to sense the position of the game's electronic ball and control a virtual paddle, a team reports in the journal Neuron. The novel achievement is part of an effort to understand how the brain learns, and how to make computers more intelligent. "We've made huge strides with silicon computing, but they're still rigid and inflexible," says Brett Kagan, an author of the study and chief scientific officer at Cortical Labs in Melbourne, Australia. "That's something we don't see with biology." For example, both computers and people can learn to make a cup of tea, Kagan says.

Artificial intelligence has predicted what the Kardashian-Jenner family would look like if they had aged naturally. The famous family, who are known for their love of cosmetic enhancements, appear very different in a digitally altered video that recently went viral on TikTok. The clip, created by popular Australian streamers Vandahood Live, estimates what Kim Kardashian, Kylie Jenner, Khloe Kardashian, Kris Jenner and Kourtney Kardashian would look like today without cosmetic intervention. A viral TikTok video has revealed using artificial intelligence (AI) what the Kardashian-Jenner family would look like if they had aged naturally. In the video, footage from last year's Keeping Up with the Kardashians finale special is played alongside doctored versions of the same clip.

The environment was something of a shift for Drake, who had spent the previous seven years as the medical response director of the Alcor Life Extension Foundation. Though it was the longtime leader in cryonics, Alcor was still a small nonprofit. It had been freezing the bodies and brains of its members, with the idea of one day bringing them back to life, since 1976. The foundation, and cryonics in general, had long survived outside of mainstream acceptance. Typically shunned by the scientific community, cryonics is best known for its appearance in sci-fi films like 2001: A Space Odyssey.