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

arXiv:2606.10703 · cs.LG, cs.CL · Submitted 2026-06-09 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-06-09

Updated: 2026-06-16

Code: https://github.com/callmeloui/observational_metrics

Terminology

• Ablation — 25× in this paper · explained in 1 episode
• Pruning — 18× in this paper · explained in 4 episodes
• Redundancy — 14× in this paper · explained in 2 episodes
• Interpretability — 9× in this paper · explained in 15 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Causal Inference — 2× in this paper · explained in 4 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Mixture-of-Experts (MoE) — 2× in this paper · explained in 7 episodes
• Activation Patching — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• OLMoE: Open Mixture-of-Experts Language Models
• SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts
• Sanity Checks for Saliency Maps
• Task-Specific Expert Pruning for Sparse Mixture-of-Experts
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks