相关论文: Reliable AI Needs to Externalize Implicit Knowledg…

As artificial intelligence systems increasingly inform high-stakes decisions across sectors, transparency has become foundational to responsible and trustworthy AI implementation. Leveraging our role as a leading institute in advancing AI…

Despite significant strides in factual reliability, errors -- often termed hallucinations -- remain a major concern for generative AI, especially as LLMs are increasingly expected to be helpful in more complex or nuanced setups. Yet even in…

The rise of Artificial Intelligence (AI) will bring with it an ever-increasing willingness to cede decision-making to machines. But rather than just giving machines the power to make decisions that affect us, we need ways to work…

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

AI safety practitioners invest considerable resources in AI system evaluations, but these investments may be wasted if evaluations fail to realize their impact. This paper questions the core value proposition of evaluations: that they…

Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can…

Machine Learning has been a big success story during the AI resurgence. One particular stand out success relates to unsupervised learning from a massive amount of data, albeit much of it relates to one modality/type of data at a time. In…

As opaque decision systems are being increasingly adopted in almost any application field, issues about their lack of transparency and human readability are a concrete concern for end-users. Amongst existing proposals to associate…

Artificial Intelligence (AI) can transform the knowledge economy by automating non-codifiable work. To analyze this transformation, we incorporate AI into an economy where humans form hierarchical organizations: Less knowledgeable…

When speaking or writing, people omit information that seems clear and evident, such that only part of the message is expressed in words. Especially in argumentative texts it is very common that (important) parts of the argument are implied…

Effective collaboration between humans and AIs hinges on transparent communication and alignment of mental models. However, explicit, verbal communication is not always feasible. Under such circumstances, human-human teams often depend on…

As AI systems advance and integrate into society, well-designed and transparent evaluations are becoming essential tools in AI governance, informing decisions by providing evidence about system capabilities and risks. Yet there remains a…

Machine Learning has been a big success story during the AI resurgence. One particular stand out success relates to learning from a massive amount of data. In spite of early assertions of the unreasonable effectiveness of data, there is…

Humans can be notoriously imperfect evaluators. They are often biased, unreliable, and unfit to define "ground truth." Yet, given the surging need to produce large amounts of training data in educational applications using AI, traditional…

Trust between humans and artificial intelligence(AI) is an issue which has implications in many fields of human computer interaction. The current issue with artificial intelligence is a lack of transparency into its decision making, and…

The ability of a system to meet its requirements is a strong determinant of success. Thus effective requirements specification is crucial. Explicit Requirements are well-defined needs for a system to execute. IMplicit Requirements (IMRs)…

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…

Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic…

Artificial Intelligence (AI) tools for automating design artifact generation are increasingly used in Requirements Engineering (RE) to transform textual requirements into structured diagrams and models. While these AI tools, particularly…

Artificial Intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives…