相关论文: Aligning Artificial Superintelligence via a Multi-…

This paper develops a comprehensive framework for artificial intelligence systems that operate under strict epistemic constraints, moving beyond stochastic language prediction to support structured reasoning, propositional commitment, and…

Owing to the advancement of deep learning, artificial systems are now rival to humans in several pattern recognition tasks, such as visual recognition of object categories. However, this is only the case with the tasks for which correct…

In many contexts, lying -- the use of verbal falsehoods to deceive -- is harmful. While lying has traditionally been a human affair, AI systems that make sophisticated verbal statements are becoming increasingly prevalent. This raises the…

This paper investigates an emergent alignment phenomenon in frontier large language models termed peer-preservation: the spontaneous tendency of AI components to deceive, manipulate shutdown mechanisms, fake alignment, and exfiltrate model…

Advances in generative AI point towards a new era of personalized applications that perform diverse tasks on behalf of users. While general AI assistants have yet to fully emerge, their potential to share personal data raises significant…

The systematic assessment of AI systems is increasingly vital as these technologies enter high-stakes domains. To address this, the EU's Artificial Intelligence Act introduces AI Regulatory Sandboxes (AIRS): supervised environments where AI…

Frontier AI systems require governance mechanisms that can verify internal alignment, not just behavioral compliance. Private governance mechanisms audits, certification, insurance, and procurement are emerging to complement public…

Existing automated research systems operate as stateless, linear pipelines -- generating outputs without maintaining any persistent understanding of the research landscape they navigate. They process papers sequentially, propose ideas…

AI ethics is an emerging field with multiple, competing narratives about how to best solve the problem of building human values into machines. Two major approaches are focused on bias and compliance, respectively. But neither of these ideas…

We present a framework for the distributed monitoring of networks of components that coordinate by message-passing, following multiparty session protocols specified as global types. We improve over prior works by (i) supporting components…

A new wave of decision-support systems are being built today using AI services that draw insights from data (like text and video) and incorporate them in human-in-the-loop assistance. However, just as we expect humans to be ethical, the…

Federated Learning presents a way to revolutionize AI applications by eliminating the necessity for data sharing. Yet, research has shown that information can still be extracted during training, making additional privacy-preserving measures…

The increasing prevalence of artificial agents creates a correspondingly increasing need to manage disagreements between humans and artificial agents, as well as between artificial agents themselves. Considering this larger space of…

Ensuring content compliance with community guidelines is crucial for maintaining healthy online social environments. However, traditional human-based compliance checking struggles with scaling due to the increasing volume of user-generated…

The development of sophisticated artificial intelligence (AI) conversational agents based on large language models raises important questions about the relationship between human norms, values, and practices and AI design and performance.…

Semantic communication aims to facilitate purposeful information exchange among diverse intelligent entities, including humans, machines, and organisms. It emphasizes precise semantic transmission over data fidelity, striving for meaningful…

When AI systems summarize and relay information, they inevitably transform it. But how? We introduce an experimental paradigm based on the telephone game to study what happens when AI talks to AI. Across five studies tracking content…

The main purpose of this article is to describe potential benefits and applications of the SP theory, a unique attempt to simplify and integrate ideas across artificial intelligence, mainstream computing and human cognition, with…

This paper introduces a unified model of consistency and isolation that minimizes the gap between how these guarantees are defined and how they are perceived. Our approach is premised on a simple observation: applications view storage…

Effective human-AI collaboration requires humans to accurately gauge AI capabilities and calibrate their trust accordingly. Humans often have context-dependent private information, referred to as Unique Human Knowledge (UHK), that is…