Related papers: humancompatible.detect: a Python Toolkit for Detec…
Advances in sensing and learning algorithms have led to increasingly mature solutions for human detection by robots, particularly in selected use-cases such as pedestrian detection for self-driving cars or close-range person detection in…
Artificial Intelligence (AI) systems are not intrinsically neutral and biases trickle in any type of technological tool. In particular when dealing with people, the impact of AI algorithms' technical errors originating with mislabeled data…
Machine learning can provide predictions with disparate outcomes, in which subgroups of the population (e.g., defined by age, gender, or other sensitive attributes) are systematically disadvantaged. In order to comply with upcoming…
Human-AI collaboration is evolving from a tool-based perspective to a partnership model where AI systems complement and enhance human capabilities. Traditional approaches often limit AI to a supportive role, missing the potential for…
Time series anomaly detection is a critical machine learning task for numerous applications, such as finance, healthcare, and industrial systems. However, even high-performing models may exhibit potential issues such as biases, leading to…
One of the difficulties of artificial intelligence is to ensure that model decisions are fair and free of bias. In research, datasets, metrics, techniques, and tools are applied to detect and mitigate algorithmic unfairness and bias. This…
A new wave of decision-support systems are being built today using AI services that draw insights from data (like text and video) and incorporate them in human-in-the-loop assistance. However, just as we expect humans to be ethical, the…
Most anomaly detection systems output scores rather than calibrated decisions, leaving practitioners to choose thresholds heuristically and without clear statistical interpretation. Conformal anomaly detection addresses this limitation by…
Many recent neural models have shown remarkable empirical results in Machine Reading Comprehension, but evidence suggests sometimes the models take advantage of dataset biases to predict and fail to generalize on out-of-sample data. While…
Large language models (LLMs) such as ChatGPT have exhibited remarkable performance in generating human-like texts. However, machine-generated texts (MGTs) may carry critical risks, such as plagiarism issues, misleading information, or…
Ensuring fairness in AI systems is critical, especially in high-stakes domains such as lending, hiring, and healthcare. This urgency is reflected in emerging global regulations that mandate fairness assessments and independent bias audits.…
In the age of advanced large language models (LLMs), the boundaries between human and AI-generated text are becoming increasingly blurred. We address the challenge of segmenting mixed-authorship text, that is identifying transition points…
Unsupervised skill discovery in Reinforcement Learning aims to mimic humans' ability to autonomously discover diverse behaviors. However, existing methods are often unconstrained, making it difficult to find useful skills, especially in…
Human-AI collaboration has the potential to transform various domains by leveraging the complementary strengths of human experts and Artificial Intelligence (AI) systems. However, unobserved confounding can undermine the effectiveness of…
In this paper, we elaborate on how AI can support diversity and inclusion and exemplify research projects conducted in that direction. We start by looking at the challenges and progress in making large language models (LLMs) more…
Many internet applications are powered by machine learned models, which are usually trained on labeled datasets obtained through either implicit / explicit user feedback signals or human judgments. Since societal biases may be present in…
The rapid advancement of generative AI has raised concerns about the authenticity of digital images, as highly realistic fake images can now be generated at low cost, potentially increasing societal risks. In response, several datasets have…
The understanding of bias in AI is currently undergoing a revolution. Initially understood as errors or flaws, biases are increasingly recognized as integral to AI systems and sometimes preferable to less biased alternatives. In this paper,…
When training powerful AI systems to perform complex tasks, it may be challenging to provide training signals which are robust to optimization. One concern is \textit{measurement tampering}, where the AI system manipulates multiple…
Machine learned models exhibit bias, often because the datasets used to train them are biased. This presents a serious problem for the deployment of such technology, as the resulting models might perform poorly on populations that are…