Related papers: Impossibility Results in AI: A Survey
Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence…
Reasoning under uncertainty is a fundamental challenge in Artificial Intelligence. As with most of these challenges, there is a harsh dilemma between the expressive power of the language used, and the tractability of the computational…
Arrow's Impossibility Theorem establishes bounds on what we can require from voting systems. Given satisfaction of a small collection of "fairness" axioms, it shows votes can only exist as dictatorships in which one voter determines all…
Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet researchers, policymakers, and technology companies lack shared terminology for discussing AI risks.…
As AI rapidly advances, the security risks posed by AI are becoming increasingly severe, especially in critical scenarios, including those posing existential risks. If AI becomes uncontrollable, manipulated, or actively evades safety…
Ttraditional safety engineering is coming to a turning point moving from deterministic, non-evolving systems operating in well-defined contexts to increasingly autonomous and learning-enabled AI systems which are acting in largely…
Despite AI's superhuman performance in a variety of domains, humans are often unwilling to adopt AI systems. The lack of interpretability inherent in many modern AI techniques is believed to be hurting their adoption, as users may not trust…
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…
Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these…
As artificial intelligence rapidly transforms society, developers and policymakers struggle to anticipate which applications will face public moral resistance. We propose that these judgments are not idiosyncratic but systematic and…
The unwavering success of deep learning in the past decade led to the increasing prevalence of deep learning methods in various application fields. However, the downsides of deep learning, most prominently its lack of trustworthiness, may…
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented…
Recently, a lot of attention has been given to undesired consequences of Artificial Intelligence (AI), such as unfair bias leading to discrimination, or the lack of explanations of the results of AI systems. There are several important…
Invention of artificial general intelligence is predicted to cause a shift in the trajectory of human civilization. In order to reap the benefits and avoid pitfalls of such powerful technology it is important to be able to control it.…
This paper establishes a fundamental Impossibility Theorem: no LLM performing non-trivial knowledge aggregation can simultaneously achieve truthful knowledge representation, semantic information conservation, complete revelation of relevant…
Developing AI systems with a human-like understanding of everyday concepts is a key step towards developing safe, reliable systems whose behavior makes sense to humans. When probing concept understanding, asking questions about plausible…
Artificial intelligence (AI) is widely promoted as a promising technological response to healthcare capacity and productivity pressures. Deployment of AI systems carries significant costs including ongoing costs of monitoring and whether…
Evaluations of generative models are now ubiquitous, and their outcomes critically shape public and scientific expectations of AI's capabilities. Yet skepticism about their reliability continues to grow. How can we know that a reported…
The paper discusses the capacities and limitations of current artificial intelligence (AI) technology to solve word problems that combine elementary knowledge with commonsense reasoning. No existing AI systems can solve these reliably. We…
Successful deployment of artificial intelligence (AI) in various settings has led to numerous positive outcomes for individuals and society. However, AI systems have also been shown to harm parts of the population due to biased predictions.…