arXiv Machine Learning June 25, 2026 By Tony Salomone, Deep Gandhi, Ali Asaria

How Modular Is a Frontier Mixture-of-Experts? A Pre-registered Causal Test in Which Apparent Expert Modularity Mostly Dissolves

Read the original on arXiv Machine Learning →

arXiv:2606. 25092v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models route each token to a few of many experts, inviting the hypothesis that experts form functional modules tied to capabilities or languages.

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

efficiency safety

arXiv AI

Jun 29

CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models

arXiv:2606. 27383v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as research assistants, yet it remains unclear whether they can calibrate research takeaways to the strength and scope of the supporting evidence.

By Yu Fu, Yongqi Kang, Yong Zhao

llms benchmarks

arXiv Machine Learning

Jun 3

Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models

arXiv:2606. 03780v1 Announce Type: cross Abstract: Causal tracing of factual recall has been studied predominantly in dense transformer language models, where interventions localize information flow to layers or feed-forward modules.

By Yuetian Lu, Ali Modarressi, Yihong Liu, Hinrich Sch\"utze

llms rag

arXiv AI

Jul 28

Hierarchical Group-Conditional Conformal Risk Control for Selective Prediction in Language Models

arXiv:2607. 24562v1 Announce Type: new Abstract: Large language models serve heterogeneous populations structured by domain, topic difficulty, and linguistic style.

By Murilo Salem, Lu\'isa B\"ohm, Daniel Pontes, Anderson Ferrugem

llms efficiency benchmarks

arXiv Machine Learning

Jun 5

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models

arXiv:2606. 05378v1 Announce Type: new Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families.

By Yongzhong Xu

llms benchmarks

arXiv Machine Learning

Aug 10

Conformal Fusion Under Missing Modalities

arXiv:2608. 07183v1 Announce Type: new Abstract: Multimodal fusion architectures typically assume all modalities are available at inference, yet sensor failures, acquisition variability, and cost constraints routinely produce incomplete observations.

By Alireza Moayedikia

multimodal benchmarks

Related stories

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

CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models

Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models

Hierarchical Group-Conditional Conformal Risk Control for Selective Prediction in Language Models

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models

Conformal Fusion Under Missing Modalities