5 papers · 1 filter
RAPTOR: Role-Aware Private Training for Mixture-of-Experts
Duc Dm, Khai Le-Duc, Nguyen Do +18
Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see all data while experts only se…
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
Rishit Dagli, Abir Harrasse, Luke Zhang +4
Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data. The gold standard for TDA relies on causal interventions, observing how a model chan…
CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs
Florent Draye, Vedant Palit, Abir Harrasse +8
Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information. Recent approaches based on dictionary learning and transcoders…
Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models
Moritz Miller, Florent Draye, Bernhard Schölkopf
A central premise in mechanistic interpretability is that meaningful concepts in language models are represented by linear features in activation space. For such features to suppor…
Intrinsically Interpretable Attention via Sparse Post-Training
Florent Draye, Anson Lei, Hsiao-Ru Pan +2
We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-…