4 papers
Spectral Archaeology: The Causal Topology of Model Evolution
Valentin Noël
Behavioral benchmarks tell us \textit{what} a model does, but not \textit{how}. We introduce a training-free mechanistic probe using attention-graph spectra. Treating each layer as…
Catching Contamination Before Generation: Spectral Kill Switches for Agents
Valentin Noël
Agentic language models compose multi step reasoning chains, yet intermediate steps can be corrupted by inconsistent context, retrieval errors, or adversarial inputs, which makes p…
Training-Free Spectral Fingerprints of Voice Processing in Transformers
Valentin Noël
Different transformer architectures implement identical linguistic computations via distinct connectivity patterns, yielding model imprinted ``computational fingerprints'' detectab…
A Graph Signal Processing Framework for Hallucination Detection in Large Language Models
Valentin Noël
Large language models achieve impressive results but distinguishing factual reasoning from hallucinations remains challenging. We propose a spectral analysis framework that models…