Related papers: Impossibility Results in AI: A Survey

The inner alignment problem, which asserts whether an arbitrary artificial intelligence (AI) model satisfices a non-trivial alignment function of its outputs given its inputs, is undecidable. This is rigorously proved by Rice's theorem,…

This manuscript establishes information-theoretic limitations for robustness of AI security and alignment by extending G\"odel's incompleteness theorem to AI. Knowing these limitations and preparing for the challenges they bring is…

The impossibility theorem of fairness is a foundational result in the algorithmic fairness literature. It states that outside of special cases, one cannot exactly and simultaneously satisfy all three common and intuitive definitions of…

Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance. However they have been empirically found to pose serious security issues. This paper systematizes our…

Ensuring that artificial intelligence (AI) systems satisfy formal safety and policy constraints is a central challenge in safety-critical domains. While limitations of verification are often attributed to combinatorial complexity and model…

Artificial intelligence (AI) model creators commonly attach restrictive terms of use to both their models and their outputs. These terms typically prohibit activities ranging from creating competing AI models to spreading disinformation.…

Certainty around the regulatory environment is crucial to enable responsible AI innovation and foster the social acceptance of these powerful new technologies. One notable source of uncertainty is, however, that the existing legal liability…

In this position paper, I argue that the best way to help and protect humans using AI technology is to make them aware of the intrinsic limitations and problems of AI algorithms. To accomplish this, I suggest three ethical guidelines to be…

Artificial Intelligence (AI) is becoming the corner stone of many systems used in our daily lives such as autonomous vehicles, healthcare systems, and unmanned aircraft systems. Machine Learning is a field of AI that enables systems to…

Modern applications of AI involve training and deploying machine learning models across heterogeneous and potentially massive environments. Emerging diversity of data not only brings about new possibilities to advance AI systems, but also…

A recent paper (van Rooij et al. 2024) claims to have proved that achieving human-like intelligence using learning from data is intractable in a complexity-theoretic sense. We point out that the proof relies on an unjustified assumption…

While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objective) has thus far hindered their use in critical applications…

Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a…

This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpretability can be formally tested or designed for. We posit…

Decision theory formally solves the problem of rational agents in uncertain worlds if the true environmental prior probability distribution is known. Solomonoff's theory of universal induction formally solves the problem of sequence…

In this paper, we propose "Confident AI" as a means to designing Artificial Intelligence (AI) and Machine Learning (ML) systems with both algorithm and user confidence in model predictions and reported results. The 4 basic tenets of…

This article discusses the possibility of predicting human behavior in a mechanism. Such a mechanism will have certain properties, which are defined and discussed here. Here it is shown that, unfortunately, certain property combinations are…

While large-scale models such as LLMs and diffusion models have achieved practical success, public institutions have emphasized the importance of explainability in AI. Existing methods for explaining AI, however, are not designed to provide…

This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some outcome other than the truth. We first survey empirical…

Arrow's Impossibility Theorem is a seminal result of Social Choice Theory that demonstrates the impossibility of ranked-choice decision-making processes to jointly satisfy a number of intuitive and seemingly desirable constraints. The…