相关论文: Building Better Deception Probes Using Targeted In…

Language models can distinguish between testing and deployment phases -- a capability known as evaluation awareness. This has significant safety and policy implications, potentially undermining the reliability of evaluations that are…

Exploratory searches are characterized by under-specified goals and evolving query intents. In such scenarios, retrieval models that can capture user-specified nuances in query intent and adapt results accordingly are desirable --…

In this research we propose a new method for training predictive machine learning models for prescriptive applications. This approach, which we refer to as coupled validation, is based on tweaking the validation step in the standard…

People are not very good at detecting lies, which may explain why they refrain from accusing others of lying, given the social costs attached to false accusations - both for the accuser and the accused. Here we consider how this social…

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…

The prevailing approach for training and evaluating paraphrase identification models is constructed as a binary classification problem: the model is given a pair of sentences, and is judged by how accurately it classifies pairs as either…

In the classic herding model, agents receive private signals about an underlying binary state of nature, and act sequentially to choose one of two possible actions, after observing the actions of their predecessors. We investigate what…

Acquiring and training on large-scale labeled data can be impractical due to cost constraints. Additionally, the use of small training datasets can result in considerable variability in model outcomes, overfitting, and learning of spurious…

Anomaly detection presents a unique challenge in machine learning, due to the scarcity of labeled anomaly data. Recent work attempts to mitigate such problems by augmenting training of deep anomaly detection models with additional labeled…

A multitude of classifiers can be trained on the same data to achieve similar performances during test time, while having learned significantly different classification patterns. This phenomenon, which we call prediction discrepancies, is…

Recent years have witnessed impressive robotic manipulation systems driven by advances in imitation learning and generative modeling, such as diffusion- and flow-based approaches. As robot policy performance increases, so does the…

In machine learning, a bias occurs whenever training sets are not representative for the test data, which results in unreliable models. The most common biases in data are arguably class imbalance and covariate shift. In this work, we aim to…

Machine learning has opened up new tools for financial fraud detection. Using a sample of annotated transactions, a machine learning classification algorithm learns to detect frauds. With growing credit card transaction volumes and rising…

Deep learning models often achieve high performance by inadvertently learning spurious correlations between targets and non-essential features. For example, an image classifier may identify an object via its background that spuriously…

Procrastination, the irrational delay of tasks, is a common occurrence in online learning. Potential negative consequences include higher risk of drop-outs, increased stress, and reduced mood. Due to the rise of learning management systems…

Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive…

Delusive attacks aim to substantially deteriorate the test accuracy of the learning model by slightly perturbing the features of correctly labeled training examples. By formalizing this malicious attack as finding the worst-case training…

Background: Deception detection through analysing language is a promising avenue using both human judgments and automated machine learning judgments. For both forms of credibility assessment, automated adversarial attacks that rewrite…

Language model-based instruction-following systems have lately shown increasing performance on many benchmark tasks, demonstrating the capability of adapting to a broad variety of instructions. However, such systems are often not designed…

Recent work has shown the potential benefit of selective prediction systems that can learn to defer to a human when the predictions of the AI are unreliable, particularly to improve the reliability of AI systems in high-stakes applications…