Related papers: Humanly Certifying Superhuman Classifiers
Achieving super-human performance in recognizing human speech has been a goal for several decades, as researchers have worked on increasingly challenging tasks. In the 1990's it was discovered, that conversational speech between two humans…
To collaborate well with robots, we must be able to understand their decision making. Humans naturally infer other agents' beliefs and desires by reasoning about their observable behavior in a way that resembles inverse reinforcement…
Classification is a ubiquitous and fundamental problem in artificial intelligence and machine learning, with extensive efforts dedicated to developing more powerful classifiers and larger datasets. However, the classification task is…
As modern video games become increasingly complex, traditional manual testing methods are proving costly and inefficient, limiting the ability to ensure high-quality game experiences. While advancements in Artificial Intelligence (AI) offer…
Machine learning (ML) models are increasingly being used in application domains that often involve working together with human experts. In this context, it can be advantageous to defer certain instances to a single human expert when they…
Despite significant developments in Proof Theory, surprisingly little attention has been devoted to the concept of proof verifier. In particular, the mathematical community may be interested in studying different types of proof verifiers…
Uncertainty quantification is essential in human-machine collaboration, as human agents tend to adjust their decisions based on the confidence of the machine counterpart. Reliably calibrated model uncertainties, hence, enable more effective…
Most modern approaches for audio processing are opaque, in the sense that they do not provide an explanation for their decisions. For this reason, various methods have been proposed to explain the outputs generated by these models. Good…
Advances in deep learning systems have allowed large models to match or surpass human accuracy on a number of skills such as image classification, basic programming, and standardized test taking. As the performance of the most capable…
Artificial intelligence (AI) provides considerable opportunities to assist human work. However, one crucial challenge of human-AI collaboration is that many AI algorithms operate in a black-box manner where the way how the AI makes…
The use of Artificial Intelligence (AI), or more generally data-driven algorithms, has become ubiquitous in today's society. Yet, in many cases and especially when stakes are high, humans still make final decisions. The critical question,…
Machine learning may enable the automated generation of test oracles. We have characterized emerging research in this area through a systematic literature review examining oracle types, researcher goals, the ML techniques applied, how the…
Explanations are hypothesized to improve human understanding of machine learning models and achieve a variety of desirable outcomes, ranging from model debugging to enhancing human decision making. However, empirical studies have found…
Neural networks need big annotated datasets for training. However, manual annotation can be too expensive or even unfeasible for certain tasks, like multi-person 2D pose estimation with severe occlusions. A remedy for this is synthetic data…
We revisit the foundations of fairness and its interplay with utility and efficiency in settings where the training data contain richer labels, such as individual types, rankings, or risk estimates, rather than just binary outcomes. In this…
Past analyses of reinforcement learning from human feedback (RLHF) assume that the human evaluators fully observe the environment. What happens when human feedback is based only on partial observations? We formally define two failure cases:…
People work with AI systems to improve their decision making, but often under- or over-rely on AI predictions and perform worse than they would have unassisted. To help people appropriately rely on AI aids, we propose showing them behavior…
Scalable oversight protocols aim to empower evaluators to accurately verify AI models more capable than themselves. However, human evaluators are subject to biases that can lead to systematic errors. We conduct two studies examining the…
Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support…
Automated fact-checking systems often struggle with trustworthiness, as their generated explanations can include hallucinations. In this work, we explore evidence attribution for fact-checking explanation generation. We introduce a novel…