Sarah Fabi

Mercedes-Benz AG

We design a battery of semantic illusions and cognitive reflection tests, aimed to elicit intuitive yet erroneous responses. We administer these tasks, traditionally used to study reasoning and decision-making in humans, to OpenAI’s generative pre-trained transformer model family. The results show that as the models expand in size and linguistic pr...

The field of artificial intelligence (AI) alignment aims to investigate whether AI technologies align with human interests and values and function in a safe and ethical manner. AI alignment is particularly relevant for large language models (LLMs), which have the potential to exhibit unintended behavior due to their ability to learn and adapt in wa...

Artificial intelligence (AI) technologies revolutionize vast fields of society. Humans using these systems are likely to expect them to work in a potentially hyperrational manner. However, in this study, we show that some AI systems, namely large language models (LLMs), exhibit behavior that strikingly resembles human-like intuition - and the many...

With the increasing effectiveness of one-/few-shot learning techniques in the context of handwritten character generation and recognition, the call to extend the commonly associated Omniglot challenge is becoming more pressing. However, the sequential Omniglot dataset represents unrealistically written characters. Therefore, we present new data, a...

Learning to write is characterized by bottom-up mimicking of characters and top-down writing from memory. We introduce a CNN-RNN model that implements both pathways: It can (i) directly write a letter by generating a motion trajectory given an image, (ii) first classify the character in the image and then determine its motion trajectory `from memor...

People detect painful expressions more easily in members of their racial ingroup than outgroup. Here, we wanted to investigate this racial bias with a machine learning model trained to detect activations of different action units of painful facial expressions. We examined whether the model detected higher action unit activation for European than Af...

This paper stresses the importance of biases in the field of artificial intelligence (AI) in two regards. First, in order to foster efficient algorithmic decision-making in complex, unstable, and uncertain real-world environments, we argue for the structurewise implementation of human cognitive biases in learning algorithms. Secondly, we argue that...

The ability to develop representations of components and to recombine them in a new but compositionally meaningful manner is considered a hallmark of human cognition, which has not been reached by machines, yet. The Omniglot challenge taps into this deficit by posing several one-shot/few-shot generation and classification tasks of handwritten chara...

When comparing human with artificial intelligence, one major difference is apparent: Humans can generalize very broadly from sparse data sets because they are able to recombine and reintegrate data components in compositional manners. To investigate differences in efficient learning, Joshua B. Tenenbaum and colleagues developed the character challe...

When comparing human with artificial intelligence, one major difference is apparent: Humans can generalize very broadly from sparse data sets because they are able to recombine and reintegrate data components in compositional manners. To investigate differences in efficient learning, Joshua B. Tenenbaum and colleagues developed the character challe...

Empathic concern and personal distress are empathic responses that may result when observing someone in discomfort. Even though these empathic responses have received much attention in past research, it is still unclear which conditions contribute to their respective experience. Hence, the main goal of this study was to examine if dispositional emp...

The aim of this study was to identify racial bias influences on empathic processing from early stimulus encoding, over categorization until late motor processing stages by comparing brain responses (electroencephalogram) to pictures of fair- and dark-colored hands in painful or neutral daily-life situations. Participants performed a pain judgment t...

The present study investigated the nature and chronometry of empathy for pain influences on perceptual and motor processes. Thus, event-related brain potentials (ERPs), response force (RF) and oscillatory electroencephalography (EEG) activity were measured while participants were presented with pictures of body parts in painful or neutral situation...