Related papers: Interpretability as Alignment: Making Internal Und…

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…

Ante-hoc interpretability has become the holy grail of explainable artificial intelligence for high-stakes domains such as healthcare; however, this notion is elusive, lacks a widely-accepted definition and depends on the operational…

Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…

Artificial Intelligence (AI) systems are increasingly deployed in legal contexts, where their opacity raises significant challenges for fairness, accountability, and trust. The so-called ``black box problem'' undermines the legitimacy of…

To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multiple interactions, where predictable and desirable behavior is reinforced over time. Providing the system's users with some…

What is it to interpret the outputs of an opaque machine learning model. One approach is to develop interpretable machine learning techniques. These techniques aim to show how machine learning models function by providing either model…

The need for transparency of predictive systems based on Machine Learning algorithms arises as a consequence of their ever-increasing proliferation in the industry. Whenever black-box algorithmic predictions influence human affairs, the…

Explainability and its emerging counterpart contestability have become important normative and design principles for trustworthy AI as they enable users and subjects to understand and challenge AI decisions. However, realizing these…

This study explores how AI-powered digital innovations are reshaping organisational accountability in a transnational governance context. As AI systems increasingly mediate decision-making in domains such as auditing and financial…

To develop general-purpose collaborative agents, humans need reliable AI systems that can (1) adapt to new domains and (2) transparently reason with uncertainty to allow for verification and correction. Black-box models demonstrate powerful…

Mechanistic interpretability is an emerging diagnostic approach for neural models that has gained traction in broader natural language processing domains. This paradigm aims to provide attribution to components of neural systems where…

Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains, such as criminal justice and consumer finance, which directly affect human well-being. However, if AI is to improve people's…

Safety-critical Autonomous Systems require trustworthy and transparent decision-making process to be deployable in the real world. The advancement of Machine Learning introduces high performance but largely through black-box algorithms. We…

The rapid integration of artificial intelligence (AI) into various industries has introduced new challenges in governance and regulation, particularly regarding the understanding of complex AI systems. A critical demand from decision-makers…

AI systems are increasingly governed by natural language principles, yet a key challenge arising from reliance on language remains underexplored: interpretive ambiguity. As in legal systems, ambiguity arises both from how these principles…

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…

Mechanistic Interpretability aims to understand neural networks through causal explanations. We argue for the Explanatory View Hypothesis: that Mechanistic Interpretability research is a principled approach to understanding models because…

Causal relationships play a pivotal role in research within the field of public administration. Ensuring reliable causal inference requires validating the predictability of these relationships, which is a crucial precondition. However,…

This paper provides empirical concerns about post-hoc explanations of black-box ML models, one of the major trends in AI explainability (XAI), by showing its lack of interpretability and societal consequences. Using a representative…

Mechanistic interpretability has transformed the analysis of transformer circuits by decomposing model behavior into competing algorithms, identifying phase transitions during training, and deriving closed-form predictions for when and why…