Related papers: A Causal Framework to Evaluate Racial Bias in Law …

Causal inference, estimating causal effects from observational data, is a fundamental tool in many disciplines. Of particular importance across a variety of domains is the continuous treatment setting, where the variable of intervention has…

The widespread adoption of ML systems across critical domains like hiring, finance, and healthcare raises growing concerns about their potential for discriminatory decision-making based on protected attributes. While efforts to ensure…

Trajectory datasets of road users have become more important in the last years for safety validation of highly automated vehicles. Several naturalistic trajectory datasets with each more than 10.000 tracks were released and others will…

Existing approaches to bias evaluation in large language models (LLMs) trade ecological validity for statistical control, relying either on artificial prompts that poorly reflect real-world use or on naturalistic tasks that lack scale and…

Recently, high-performing code generation systems based on large language models have surfaced. They are trained on massive corpora containing much more natural text than actual executable computer code. This work shows that current code…

When teaching and discussing statistical assumptions, our focus is oftentimes placed on how to test and address potential violations rather than the effects of violating assumptions on the estimates produced by our statistical models. The…

Social biases inherent in large language models (LLMs) raise significant fairness concerns. Retrieval-Augmented Generation (RAG) architectures, which retrieve external knowledge sources to enhance the generative capabilities of LLMs, remain…

Biases with respect to socially-salient attributes of individuals have been well documented in evaluation processes used in settings such as admissions and hiring. We view such an evaluation process as a transformation of a distribution of…

Though notable progress has been made, neural-based aspect-based sentiment analysis (ABSA) models are prone to learn spurious correlations from annotation biases, resulting in poor robustness on adversarial data transformations. Among the…

Human biases have been shown to influence the performance of models and algorithms in various fields, including Natural Language Processing. While the study of this phenomenon is garnering focus in recent years, the available resources are…

Causal structure learning with data from multiple contexts carries both opportunities and challenges. Opportunities arise from considering shared and context-specific causal graphs enabling to generalize and transfer causal knowledge across…

No man is an island, as individuals interact and influence one another daily in our society. When social influence takes place in experiments on a population of interconnected individuals, the treatment on a unit may affect the outcomes of…

Large Vision Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet they also exhibit notable social biases. These biases often manifest as unintended associations between neutral concepts and sensitive human…

Identifying the causes of a model's unfairness is an important yet relatively unexplored task. We look into this problem through the lens of training data - the major source of unfairness. We ask the following questions: How would the…

AI-driven models are increasingly deployed in operational analytics solutions, for instance, in investigative journalism or the intelligence community. Current approaches face two primary challenges: ethical and privacy concerns, as well as…

Face recognition systems are widely deployed in safety-critical applications, including law enforcement, yet they exhibit bias across a range of socio-demographic dimensions, such as gender and race. Conventional wisdom dictates that model…

In this article we explore the data available through the Stanford Open Policing Project. The data consist of information on millions of traffic stops across close to 100 different cities and highway patrols. Using a variety of metrics, we…

Many agencies have adopted the FHWA-recommended systemic approach to traffic safety, an essential supplement to the traditional hotspot crash analysis which develops region-wide safety projects based on identified risk factors. However,…

Enhancing the performance of trajectory planners for lane - changing vehicles is one of the key challenges in autonomous driving within human - machine mixed traffic. Most existing studies have not incorporated human drivers' prior…

Incident monitoring can drive safety improvements in high-reliability industries and population-scale technologies, but remains underdeveloped in AI governance. Public databases catalog thousands of AI incidents, but simple incident counts…