5 papers
Mechanistic Interpretability Needs Philosophy
Iwan Williams, Ninell Oldenburg, Ruchira Dhar +6
Mechanistic interpretability (MI) aims to explain how neural networks work by uncovering their underlying mechanisms. As the field grows in influence, it is increasingly important…
Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Research
Ninell Oldenburg, Ruchira Dhar, Anders Søgaard
In this paper, we argue that current AI research operates on a spectrum between two different underlying conceptions of intelligence: Intelligence Realism, which holds that intelli…
On the Measure of a Model: From Intelligence to Generality
Ruchira Dhar, Ninell Oldenburg, Anders Soegaard
Benchmarks such as ARC, Raven-inspired tests, and the Blackbird Task are widely used to evaluate the intelligence of large language models (LLMs). Yet, the concept of intelligence…
The Stories We Govern By: AI, Risk, and the Power of Imaginaries
Ninell Oldenburg, Gleb Papyshev
This paper examines how competing sociotechnical imaginaries of artificial intelligence (AI) risk shape governance decisions and regulatory constraints. Drawing on concepts from sc…
Beyond Technocratic XAI: The Who, What & How in Explanation Design
Ruchira Dhar, Stephanie Brandl, Ninell Oldenburg +1
The field of Explainable AI (XAI) offers a wide range of techniques for making complex models interpretable. Yet, in practice, generating meaningful explanations is a context-depen…