arXiv Machine Learning By Amir Asiaee

Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

Read the original on arXiv Machine Learning →

arXiv:2607. 08349v1 Announce Type: new Abstract: Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed model to the original one.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jun 10

From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models

arXiv:2606. 10703v1 Announce Type: new Abstract: Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of targeted interventions on specific computations; in Pearl's terms, they treat rung-1 associational evidence as if it supported rung-2 interventional conclusions, a move whose validity is rarely tested.

By Leonard Engmann, Christian Medeiros Adriano, Holger Giese
arXiv AI
Jun 3

Causal Neural Probabilistic Circuits

arXiv:2603. 01372v2 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) enhance the interpretability of end-to-end neural networks by introducing a layer of concepts and predicting the class label from the concept predictions.

By Weixin Chen, Han Zhao
Hugging Face Trending Papers
Jul 14

Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs

Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when their internal belief is unchanged. We cast this as a failure of internal incentive-compatibility (IC) and present a method for learning and certifying counterfactual report mediators that hold a model's reports to a causal contract: invariant to forbidden influences (pressure, prestige, restyling) and responsive to licensed ones (genuine evidence).