Showing 2026Show all
3 papers · 1 filter
cs.CL2026
Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation
Nura Aljaafari, Andre Freitas
Mechanistic interpretability has identified transformer circuits, but lacks a shared vocabulary for describing how their functions compose across tasks and architectures. We introd…
cs.CL2026
Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation
Nura Aljaafari, Marco Valentino, André Freitas
Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but w…
cs.LG2026
From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
Nura Aljaafari, Danilo S. Carvalho, Andre Freitas
Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimental artefacts: there is no s…