Related papers: What Values Do ImageNet-trained Classifiers Enact?

This paper examines potential biases and inconsistencies in emotional evocation of images produced by generative artificial intelligence (AI) models and their potential bias toward negative emotions. In particular, we assess this bias by…

We introduce a framework for reasoning about what meaning is captured by the neurons in a trained neural network. We provide a strategy for discovering meaning by training a second model (referred to as an observer model) to classify the…

Can neural networks be applied in voting theory, while satisfying the need for transparency in collective decisions? We propose axiomatic deep voting: a framework to build and evaluate neural networks that aggregate preferences, using the…

Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI…

Detecting AI risks becomes more challenging as stronger models emerge and find novel methods such as Alignment Faking to circumvent these detection attempts. Inspired by how risky behaviors in humans (i.e., illegal activities that may hurt…

There has been increasing awareness of ethical issues in machine learning, and fairness has become an important research topic. Most fairness efforts in computer vision have been focused on human sensing applications and preventing…

Large vision-language models (VLMs) can jointly interpret images and text, but they are also prone to absorbing and reproducing harmful social stereotypes when visual cues such as age, gender, race, clothing, or occupation are present. To…

Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet the field studies it without a shared foundation, conflating properties of the evaluation…

Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate…

Computer vision systems are designed to work well within the context of everyday photography. However, artists often render the world around them in ways that do not resemble photographs. Artwork produced by people is not constrained to…

Transfer learning is crucial for medical imaging, yet the selection of source datasets often relies on researchers' intuition rather than systematic principles, which can impact the generalizability of algorithms and, thus, patient…

The rapid advancement of Visual Language Models (VLMs) has enabled sophisticated analysis of visual content, leading to concerns about the inference of sensitive user attributes and subsequent privacy risks. While technical capabilities of…

We use a design workbook of speculative scenarios as a values elicitation activity with 14 participants. The workbook depicts use case scenarios with smart home camera technologies that involve surveillance and uneven power relations. The…

The adoption of generative AI technologies is swiftly expanding. Services employing both linguistic and mul-timodal models are evolving, offering users increasingly precise responses. Consequently, human reliance on these technologies is…

Profile images on social networks are users' opportunity to present themselves and to affect how others judge them. We examine what Facebook images say about users' perceived and measured intelligence. 1,122 Facebook users completed a…

In this paper, we address the problem of detecting expressions of moral values in tweets using content analysis. This is a particularly challenging problem because moral values are often only implicitly signaled in language, and tweets…

Image generation models are poised to become ubiquitous in a range of applications. These models are often fine-tuned and evaluated using human quality judgments that assume a universal standard, failing to consider the subjectivity of such…

AI alignment considers how we can encode AI systems in a way that is compatible with human values. The normative side of this problem asks what moral values or principles, if any, we should encode in AI. To this end, we present a framework…

Gestalt psychologists have identified a range of conditions in which humans organize elements of a scene into a group or whole, and perceptual grouping principles play an essential role in scene perception and object identification.…

We introduce a new computational model of moral decision making, drawing on a recent theory of commonsense moral learning via social dynamics. Our model describes moral dilemmas as a utility function that computes trade-offs in values over…