Related papers: Interpretability as Alignment: Making Internal Und…
The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…
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…
The need for interpretable and accountable intelligent systems grows along with the prevalence of artificial intelligence applications used in everyday life. Explainable intelligent systems are designed to self-explain the reasoning behind…
While the exact definition and implementation of accountability depend on the specific context, at its core accountability describes a mechanism that will make decisions transparent and often provides means to sanction "bad" decisions. As…
The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI…
Trust in clinical artificial intelligence (AI) cannot be reduced to model accuracy, fluency of generation, or overall positive user impression. In medicine, trust must be engineered as a measurable system property grounded in evidence,…
Existing AI disclosure mandates in scholarship require that AI assistance be reported but leave transparency philosophically unspecified: they fix the duty without explaining what the duty serves. We argue that ethical inquiry is…
Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic process, an interpretation, that explains the model's decision process on that…
Neural networks organize information according to the hierarchical, multi-scale structure of natural data. Methods to interpret model internals should be similarly scale-aware, explicitly tracking how features compose across resolutions and…
This paper grounds ethics in evolutionary biology, viewing moral norms as adaptive mechanisms that render cooperation fitness-viable under selection pressure. Current alignment approaches add ethics post hoc, treating it as an external…
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…
Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…
When developing AI systems that interact with humans, it is essential to design both a system that can understand humans, and a system that humans can understand. Most deep network based agent-modeling approaches are 1) not interpretable…
Autonomous vehicles often make complex decisions via machine learning-based predictive models applied to collected sensor data. While this combination of methods provides a foundation for real-time actions, self-driving behavior primarily…
Developing and implementing AI-based solutions help state and federal government agencies, research institutions, and commercial companies enhance decision-making processes, automate chain operations, and reduce the consumption of natural…
As Artificial Intelligence (AI) systems proliferate, the need for systematic, transparent, and actionable processes for evaluating them is growing. While many resources exist to support AI evaluation, they have several limitations. Few…
Although "black box" models such as Artificial Neural Networks, Support Vector Machines, and Ensemble Approaches continue to show superior performance in many disciplines, their adoption in the sensitive disciplines (e.g., finance,…
Understanding how ML models work is a prerequisite for responsibly designing, deploying, and using ML-based systems. With interpretability approaches, ML can now offer explanations for its outputs to aid human understanding. Though these…
Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal…
Society's capacity for algorithmic problem-solving has never been greater. Artificial Intelligence is now applied across more domains than ever, a consequence of powerful abstractions, abundant data, and accessible software. As capabilities…