Related papers: Admissibility Alignment
Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…
Safety and trustworthiness are indispensable requirements for real-world applications of AI systems using large language models (LLMs). This paper formulates human value alignment as an optimization problem of the language model policy to…
Present practice of deciding on regulation faces numerous problems that make adopted regulations static, unexplained, unduly influenced by powerful interest groups, and stained with a perception of illegitimacy. These well-known problems…
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…
Whenever an AI model is used to predict a relevant (binary) outcome in AI-assisted decision making, it is widely agreed that, together with each prediction, the model should provide an AI confidence value. However, it has been unclear why…
Current AI systems increasingly operate in contexts where their outputs directly trigger real-world actions. Most existing approaches to AI safety, risk management, and governance focus on post-hoc validation, probabilistic risk estimation,…
Indirect comparisons of treatment-specific outcomes across separate studies often inform decision-making in the absence of head-to-head randomized comparisons. Differences in baseline characteristics between study populations may introduce…
This paper proposes a comprehensive analysis of existing concepts coming from different disciplines tackling the notion of intelligence, namely psychology and engineering, and from disciplines aiming to regulate AI innovations, namely AI…
A global challenge in artificial intelligence (AI) regulation lies in achieving effective risk management without compromising innovation and technical progress. The European Union (EU) Artificial Intelligence Act represents the first…
Abstract Like electoral systems, decision-making methods are also vulnerable to manipulation by decision-makers. The ability to effectively defend against such threats can only come from thoroughly understanding the manipulation mechanisms.…
Static program analysis today takes an analytical approach which is quite suitable for a well-scoped system. Data- and control-flow is taken into account. Special cases such as pointers, procedures, and undefined behavior must be handled. A…
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…
We present Manifold Alignment Determination (MAD), an algorithm for learning alignments between data points from multiple views or modalities. The approach is capable of learning correspondences between views as well as correspondences…
This paper describes a generalizable model evaluation method that can be adapted to evaluate AI/ML models across multiple criteria including core scientific principles and more practical outcomes. Emerging from prediction competitions in…
Regulations govern many aspects of citizens' daily lives. Governments and businesses routinely automate these in the form of coded rules (e.g., to check a citizen's eligibility for specific benefits). However, the path to automation is long…
In this position paper, we argue that understanding the relation between structure in the data distribution and structure in trained models is central to AI alignment. First, we discuss how two neural networks can have equivalent…
Human core object recognition depends on the selective use of visual information, but the strategies guiding these choices are difficult to measure directly. We present MAPS (Masked Attribution-based Probing of Strategies), a behaviorally…
Addressing the need for explainable Machine Learning has emerged as one of the most important research directions in modern Artificial Intelligence (AI). While the current dominant paradigm in the field is based on black-box models,…
Probabilistic Programming Languages (PPLs) allow users to encode statistical inference problems and automatically apply an inference algorithm to solve them. Popular inference algorithms for PPLs, such as sequential Monte Carlo (SMC) and…
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…