相关论文: Post-Selections in AI and How to Avoid Them

Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is subject to human labeling bias. Similarly, there are multiple…

Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted) and model utility (how good is the performance on accepted…

While natural-language explanations from large language models (LLMs) are widely adopted to improve transparency and trust, their impact on objective human-AI team performance remains poorly understood. We identify a Persuasion Paradox:…

This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a classic 64-item syllogistic reasoning benchmark. More broadly, the benchmark is relevant to ongoing…

Online experiments (A/B tests) are widely regarded as the gold standard for evaluating recommender system variants and guiding launch decisions. However, a variety of biases can distort the results of the experiment and mislead…

In recent work, we identified and studied a small cohort of Twitter users whose pregnancies with birth defect outcomes could be observed via their publicly available tweets. Exploiting social media's large-scale potential to complement the…

Human-AI collaboration is typically offered in one of two of user control levels: guidance, where the AI provides suggestions and the human makes the final decision, and delegation, where the AI acts autonomously within user-defined…

Self-learning is a classical approach for learning with both labeled and unlabeled observations which consists in giving pseudo-labels to unlabeled training instances with a confidence score over a predetermined threshold. At the same time,…

In today's world, AI programs powered by Machine Learning are ubiquitous, and have achieved seemingly exceptional performance across a broad range of tasks, from medical diagnosis and credit rating in banking, to theft detection via video…

Recent studies have noted an intriguing phenomenon termed Neural Collapse, that is, when the neural networks establish the right correlation between feature spaces and the training targets, their last-layer features, together with the…

Despite the practical success of Artificial Intelligence (AI), current neural AI algorithms face two significant issues. First, the decisions made by neural architectures are often prone to bias and brittleness. Second, when a chain of…

Positive Unlabeled (PU) learning is widely used in many applications, where a binary classifier is trained on the datasets consisting of only positive and unlabeled samples. In this paper, we improve PU learning over state-of-the-art from…

Artificial intelligence's (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language…

Adaptive interventions (AIs) are increasingly becoming popular in medical and behavioral sciences. An AI is a sequence of individualized intervention options that specify for whom and under what conditions different intervention options…

This study proposes an "AI Development Support" approach that, unlike conventional AI Alignment-which aims to forcefully inject human values-supports the ethical and moral development of AI itself. As demonstrated by the Orthogonality…

Adversarial Training (AT) is one of the most effective methods to train robust Deep Neural Networks (DNNs). However, AT creates an inherent trade-off between clean accuracy and adversarial robustness, which is commonly attributed to the…

Deep learning (DL)-based systems can exhibit unexpected behavior when exposed to out-of-distribution (OOD) scenarios, posing serious risks in safety-critical domains such as malware detection and autonomous driving. This underscores the…

As AI systems appear to exhibit ever-increasing capability and generality, assessing their true potential and safety becomes paramount. This paper contends that the prevalent evaluation methods for these systems are fundamentally…

Backpropagation (BP) is the standard algorithm for training the deep neural networks that power modern artificial intelligence including large language models. However, BP is energy inefficient and unlikely to be implemented by the brain.…

Changepoint detection methods are used in many areas of science and engineering, e.g., in the analysis of copy number variation data, to detect abnormalities in copy numbers along the genome. Despite the broad array of available tools,…