Artificial Intelligence (cs.AI)

Abstract: Physical artificial intelligence can prove to be one of the most important challenges of the artificial intelligence. The governance of physical artificial intelligence would define its responsible intelligent application in the society.

Abstract: We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI). Different from existing data-driven weather forecast methods, FengWu solves the medium-range forecast problem from a multi-modal and multi-task perspective. Specifically, a deep learning architecture equipped with model-specific encoder-decoders and cross-modal fusion Transformer is elaborately designed, which is learned under the supervision of an uncertainty loss to balance the optimization of different predictors in a region-adaptive manner. Besides this, a replay buffer mechanism is introduced to improve medium-range forecast performance. With 39-year data training based on the ERA5 reanalysis, FengWu is able to accurately reproduce the atmospheric dynamics and predict the future land and atmosphere states at 37 vertical levels on a 0.25{\deg} latitude-longitude resolution. Hindcasts of 6-hourly weather in 2018 based on ERA5 demonstrate that FengWu performs better than GraphCast in predicting 80\% of the 880 reported predictands, e.g., reducing the root mean square error (RMSE) of 10-day lead global z500 prediction from 733 to 651 $m^{2}/s^2$. In addition, the inference cost of each iteration is merely 600ms on NVIDIA Tesla A100 hardware. The results suggest that FengWu can significantly improve the forecast skill and extend the skillful global medium-range weather forecast out to 10.75 days lead (with ACC of z500 > 0.6) for the first time.

Abstract: The retriever-reader framework is popular for open-domain question answering (ODQA), where a retriever samples for the reader a set of relevant candidate passages from a large corpus. A key assumption behind this method is that high relevance scores from the retriever likely indicate high answerability from the reader, which implies a high probability that the retrieved passages contain answers to a given question. In this work, we empirically dispel this belief and observe that recent dense retrieval models based on DPR often rank unanswerable counterfactual passages higher than their answerable original passages. To address such answer-unawareness in dense retrievers, we seek to use counterfactual samples as additional training resources to better synchronize the relevance measurement of DPR with the answerability of question-passage pairs. Specifically, we present counterfactually-Pivoting Contrastive Learning (PiCL), a novel representation learning approach for passage retrieval that leverages counterfactual samples as pivots between positive and negative samples in their learned embedding space. We incorporate PiCL into the retriever training to show the effectiveness of PiCL on ODQA benchmarks and the robustness of the learned models.

Abstract: The role of an expert in the decision-making process is crucial, as the final recommendation depends on his disposition, clarity of mind, experience, and knowledge of the problem. However, the recommendation also depends on their honesty. But what if the expert is dishonest? Then, the answer on how difficult it is to manipulate in a given case becomes essential. In the presented work, we consider manipulation of a ranking obtained by comparing alternatives in pairs. More specifically, we propose an algorithm for finding an almost optimal way to swap the positions of two selected alternatives. Thanks to this, it is possible to determine how difficult such manipulation is in a given case. Theoretical considerations are illustrated by a practical example.

Abstract: Skilled employees are usually seen as the most important pillar of an organization. Despite this, most organizations face high attrition and turnover rates. While several machine learning models have been developed for analyzing attrition and its causal factors, the interpretations of those models remain opaque. In this paper, we propose the HR-DSS approach, which stands for Human Resource Decision Support System, and uses explainable AI for employee attrition problems. The system is designed to assist human resource departments in interpreting the predictions provided by machine learning models. In our experiments, eight machine learning models are employed to provide predictions, and the results achieved by the best-performing model are further processed by the SHAP explainability process. We optimize both the correctness and explanation of the results. Furthermore, using "What-if-analysis", we aim to observe plausible causes for attrition of an individual employee. The results show that by adjusting the specific dominant features of each individual, employee attrition can turn into employee retention through informative business decisions. Reducing attrition is not only a problem for any specific organization but also, in some countries, becomes a significant societal problem that impacts the well-being of both employers and employees.

Abstract: A persistently popular topic in online social networks is the rapid and accurate discovery of bot accounts to prevent their invasion and harassment of genuine users. We propose a unified embedding framework called BOTTRINET, which utilizes textual content posted by accounts for bot detection based on the assumption that contexts naturally reveal account personalities and habits. Content is abundant and valuable if the system efficiently extracts bot-related information using embedding techniques. Beyond the general embedding framework that generates word, sentence, and account embeddings, we design a triplet network to tune the raw embeddings (produced by traditional natural language processing techniques) for better classification performance. We evaluate detection accuracy and f1score on a real-world dataset CRESCI2017, comprising three bot account categories and five bot sample sets. Our system achieves the highest average accuracy of 98.34% and f1score of 97.99% on two content-intensive bot sets, outperforming previous work and becoming state-of-the-art. It also makes a breakthrough on four content-less bot sets, with an average accuracy improvement of 11.52% and an average f1score increase of 16.70%.

Abstract: Synthetic data are becoming a critical tool for building artificially intelligent systems. Simulators provide a way of generating data systematically and at scale. These data can then be used either exclusively, or in conjunction with real data, for training and testing systems. Synthetic data are particularly attractive in cases where the availability of ``real'' training examples might be a bottleneck. While the volume of data in healthcare is growing exponentially, creating datasets for novel tasks and/or that reflect a diverse set of conditions and causal relationships is not trivial. Furthermore, these data are highly sensitive and often patient specific. Recent research has begun to illustrate the potential for synthetic data in many areas of medicine, but no systematic review of the literature exists. In this paper, we present the cases for physical and statistical simulations for creating data and the proposed applications in healthcare and medicine. We discuss that while synthetics can promote privacy, equity, safety and continual and causal learning, they also run the risk of introducing flaws, blind spots and propagating or exaggerating biases.

Abstract: Chain-of-Thought (CoT) prompting can effectively elicit complex multi-step reasoning from Large Language Models~(LLMs). For example, by simply adding CoT instruction ``Let's think step-by-step'' to each input query of MultiArith dataset, GPT-3's accuracy can be improved from 17.7\% to 78.7\%. However, it is not clear whether CoT is still effective on more recent instruction finetuned (IFT) LLMs such as ChatGPT. Surprisingly, on ChatGPT, CoT is no longer effective for certain tasks such as arithmetic reasoning while still keeping effective on other reasoning tasks. Moreover, on the former tasks, ChatGPT usually achieves the best performance and can generate CoT even without being instructed to do so. Hence, it is plausible that ChatGPT has already been trained on these tasks with CoT and thus memorized the instruction so it implicitly follows such an instruction when applied to the same queries, even without CoT. Our analysis reflects a potential risk of overfitting/bias toward instructions introduced in IFT, which becomes more common in training LLMs. In addition, it indicates possible leakage of the pretraining recipe, e.g., one can verify whether a dataset and instruction were used in training ChatGPT. Our experiments report new baseline results of ChatGPT on a variety of reasoning tasks and shed novel insights into LLM's profiling, instruction memorization, and pretraining dataset leakage.