Related papers: The logic of NTQR evaluations of noisy AI agents: …
As AI systems advance, AI evaluations are becoming an important pillar of regulations for ensuring safety. We argue that such regulation should require developers to explicitly identify and justify key underlying assumptions about…
The evaluation of noisy binary classifiers on unlabeled data is treated as a streaming task: given a data sketch of the decisions by an ensemble, estimate the true prevalence of the labels as well as each classifier's accuracy on them. Two…
Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent…
If two experts disagree on a test, we may conclude both cannot be 100 per cent correct. But if they completely agree, no possible evaluation can be excluded. This asymmetry in the utility of agreements versus disagreements is explored here…
If two agents disagree in their decisions, we may suspect they are not both correct. This intuition is formalized for evaluating agents that have carried out a binary classification task. Their agreements and disagreements on a joint test…
As AI systems increasingly shape political views, defining and evaluating AI political neutrality is an urgent problem. Here, we propose a new definition of AI political neutrality and design a large-scale user study to test it, releasing a…
Reliable certification of Large Language Models (LLMs)-verifying that failure rates are below a safety threshold-is critical yet challenging. While "LLM-as-a-Judge" offers scalability, judge imperfections, noise, and bias can invalidate…
The challenge of aligning artificial intelligence (AI) with human values persists due to the abstract and often conflicting nature of moral principles and the opacity of existing approaches. This paper introduces CogniAlign, a multi-agent…
Technical and legal debates frequently suggest that "accuracy" is an objective, measurable, and purely technical property. We challenge this view, showing that evaluating AI performance fundamentally depends on context-dependent normative…
Majority voting (MV) is the prototypical ``wisdom of the crowd'' algorithm. Theorems considering when MV is optimal for group decisions date back to Condorcet's 1785 jury \emph{decision} theorem. The same error independence assumption…
In the future, AI will increasingly find its way into systems that can potentially cause physical harm to humans. For such safety-critical systems, it must be demonstrated that their residual risk does not exceed what is acceptable. This…
We present an empirical study of how both experienced tutors and non-tutors judge the correctness of tutor praise responses under different Artificial Intelligence (AI)-assisted interfaces, types of explanation (textual explanations vs.…
A well-known limitation of AI systems is presumptuousness: the tendency of AI systems to provide confident answers when information may be lacking. This challenge is particularly acute in legal applications, where a core task for attorneys,…
Most autonomous robotic agents use logic inference to keep themselves to safe and permitted behaviour. Given a set of rules, it is important that the robot is able to establish the consistency between its rules, its perception-based…
Validity, reliability, and fairness are core ethical principles embedded in classical argument-based assessment validation theory. These principles are also central to the Standards for Educational and Psychological Testing (2014) which…
Plato provides fast approximate analytics on time series, by precomputing and storing compressed time series. Plato's key novelty is the delivery of tight deterministic error guarantees for time series analytics. Plato evaluates any time…
We identify a fundamental incompatibility between the goals of accuracy, trust, and human-level reasoning in artificial intelligence (AI) systems, for strict mathematical definitions of these notions. We define accuracy of a system as the…
Identifying logical errors in complex, incomplete or even contradictory and overall heterogeneous data like students' experimentation protocols is challenging. Recognizing the limitations of current evaluation methods, we investigate the…
Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system's entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both…
It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that…