Few-shot learning is a challenging task that requires language models to generalize from limited examples. Large language models like GPT-3 and PaLM have made impressive progress in this area, but they still face difficulties in reasoning tasks such as GSM8K, a benchmark for arithmetic problems. To improve their reasoning skills, previous work has proposed to guide the language model with prompts that elicit a series of reasoning steps before giving the final answer, achieving a significant improvement on GSM8K from 17.9% to 58.1% in problem-solving rate. In this paper, we present DIVERSE (Diverse Verifier on Reasoning Step), a novel approach that further enhances the reasoning capability of language models. DIVERSE has three main components: first, it generates diverse prompts to explore different reasoning paths for the same question; second, it uses a verifier to filter out incorrect answers based on a weighted voting scheme; and third, it verifies each reasoning step individually instead of the whole chain. We evaluate DIVERSE on the latest language model code-davinci-002 and show that it achieves new state-of-the-art results on six of eight reasoning benchmarks (e.g., GSM8K 74.4% to 83.2%).

Research on Korean grammatical error correction (GEC) is limited, compared to other major languages such as English. We attribute this problematic circumstance to the lack of a carefully designed evaluation benchmark for Korean GEC. In this work, we collect three datasets from different sources (Kor-Lang8, Kor-Native, and Kor-Learner) that covers a wide range of Korean grammatical errors. Considering the nature of Korean grammar, We then define 14 error types for Korean and provide KAGAS (Korean Automatic Grammatical error Annotation System), which can automatically annotate error types from parallel corpora. We use KAGAS on our datasets to make an evaluation benchmark for Korean, and present baseline models trained from our datasets. We show that the model trained with our datasets significantly outperforms the currently used statistical Korean GEC system (Hanspell) on a wider range of error types, demonstrating the diversity and usefulness of the datasets. The implementations and datasets are open-sourced.

Although moral responsibility is not circumscribed by causality, they are both closely intermixed. Furthermore, rationally understanding the evolution of the physical world is inherently linked with the idea of causality. Thus, the decision-making applications based on automated planning inevitably have to deal with causality, especially if they consider imputability aspects or integrate references to ethical norms. The many debates around causation in the last decades have shown how complex this notion is and thus, how difficult is its integration with planning. As a result, much of the work in computational ethics relegates causality to the background, despite the considerations stated above. This paper's contribution is to provide a complete and sound translation into logic programming from an actual causation definition suitable for action languages, this definition is a formalisation of Wright's NESS test. The obtained logic program allows to deal with complex causal relations. In addition to enabling agents to reason about causality, this contribution specifically enables the computational ethics domain to handle situations that were previously out of reach. In a context where ethical considerations in decision-making are increasingly important, advances in computational ethics can greatly benefit the entire AI community.

We propose a deep importance sampling method that is suitable for estimating rare event probabilities in high-dimensional problems. We approximate the optimal importance distribution in a general importance sampling problem as the pushforward of a reference distribution under a composition of order-preserving transformations, in which each transformation is formed by a squared tensor-train decomposition. The squared tensor-train decomposition provides a scalable ansatz for building order-preserving high-dimensional transformations via density approximations. The use of composition of maps moving along a sequence of bridging densities alleviates the difficulty of directly approximating concentrated density functions. To compute expectations over unnormalized probability distributions, we design a ratio estimator that estimates the normalizing constant using a separate importance distribution, again constructed via a composition of transformations in tensor-train format. This offers better theoretical variance reduction compared with self-normalized importance sampling, and thus opens the door to efficient computation of rare event probabilities in Bayesian inference problems. Numerical experiments on problems constrained by differential equations show little to no increase in the computational complexity with the event probability going to zero, and allow to compute hitherto unattainable estimates of rare event probabilities for complex, high-dimensional posterior densities.

Adversarial training has gained great popularity as one of the most effective defenses for deep neural network and more generally for gradient-based machine learning models against adversarial perturbations on data points. This paper establishes a continuous-time approximation for the mini-max game of adversarial training. This approximation approach allows for precise and analytical comparisons between stochastic gradient descent and its adversarial training counterpart; and confirms theoretically the robustness of adversarial training from a new gradient-flow viewpoint. The analysis is then corroborated through various analytical and numerical examples.

The Bayesian Synthetic Likelihood (BSL) method is a widely-used tool for likelihood-free Bayesian inference. This method assumes that some summary statistics are normally distributed, which can be incorrect in many applications. We propose a transformation, called the Wasserstein Gaussianization transformation, that uses a Wasserstein gradient flow to approximately transform the distribution of the summary statistics into a Gaussian distribution. BSL also implicitly requires compatibility between simulated summary statistics under the working model and the observed summary statistics. A robust BSL variant which achieves this has been developed in the recent literature. We combine the Wasserstein Gaussianization transformation with robust BSL, and an efficient Variational Bayes procedure for posterior approximation, to develop a highly efficient and reliable approximate Bayesian inference method for likelihood-free problems.

Rapid advances in artificial intelligence (AI) such as Microsoft-backed OpenAI's ChatGPT are complicating governments' efforts to agree to laws governing the use of the technology. The government is consulting Australia's main science advisory body and is considering the next steps, a spokesperson for the industry and science minister said in April. The Financial Conduct Authority, one of several state regulators tasked with drawing up new guidelines covering AI, is consulting with the Alan Turing Institute and other legal and academic institutions to improve its understanding of the technology, a spokesperson said. Britain's competition regulator said on May 4 it would start examining the effect of AI on consumers, businesses and the economy, and whether new controls were needed. Britain said in March it planned to split responsibility for governing AI between its regulators for human rights, health and safety, and competition, rather than creating a new body. China's cyberspace regulator in April unveiled draft measures to manage generative AI services, saying it wanted firms to submit security assessments to authorities before they launch offerings to the public.

Software giant Adobe has announced it will integrate generative AI into its widely used Photoshop program, while downplaying fears the move will lead to job losses and mass fakes. The brand most associated with image editing will incorporate the generative AI product Adobe Firefly, which launched as a beta six weeks ago, creating a tool the company says will become a "co-pilot" to graphic design rather than a replacement for humans. Using the "generative fill" feature, Photoshop users will be able to add to, expand or remove unwanted items from images using a text prompt similar to those used by Dall-E and Midjourney, such as "long haired dachshund with long flowing rainbow hair". The generative fill feature will be available in the desktop beta from Tuesday, with a wider release set for later in 2023. Adobe has been using AI in its tools for over a decade, such as the background replacement tool in Photoshop.

Dyson's first robot vacuum, the 360 Eye, was not a great success in the US as it was quickly pulled from the market shortly after it went on sale. Now, the UK company is trying again with the 360 Vis Nav robovac, which just launched in Australia and is expected to come to the US later this year. While it lacks features like self-emptying, Dyson is promising "twice the suction" of any other robot vacuum, a new vision/navigation system and more. The motor speed has increased from 78,000 RPM on the last model to 110,000, which supposedly delivers six times the suction of other robot vacuums. It also offers a "triple-action" brush bar that allows for optimal cleaning on different surfaces.

Long-form question answering (LFQA) aims at answering complex, open-ended questions with detailed, paragraph-length responses. The de facto paradigm of LFQA necessitates two procedures: information retrieval, which searches for relevant supporting facts, and information synthesis, which integrates these facts into a coherent answer. In this paper, we introduce WebCPM, the first Chinese LFQA dataset. One unique feature of WebCPM is that its information retrieval is based on interactive web search, which engages with a search engine in real time. Following WebGPT, we develop a web search interface. We recruit annotators to search for relevant information using our interface and then answer questions. Meanwhile, the web search behaviors of our annotators would be recorded. In total, we collect 5,500 high-quality question-answer pairs, together with 14,315 supporting facts and 121,330 web search actions. We fine-tune pre-trained language models to imitate human behaviors for web search and to generate answers based on the collected facts. Our LFQA pipeline, built on these fine-tuned models, generates answers that are no worse than human-written ones in 32.5% and 47.5% of the cases on our dataset and DuReader, respectively.