Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
- Does the Order of Fine-tuning Matter and Why?
- Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping
- The Pile: An 800GB Dataset of Diverse Text for Language Modeling
- The Llama 3 Herd of Models
- Studying Large Language Model Generalization with Influence Functions
- Fresh in memory: Training-order recency is linearly encoded in language model activations
- Decoupled Weight Decay Regularization
- Qwen2.5 Technical Report
- Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Optimizer Memory Makes Shuffle Order a First-Order Source of Fine-Tuning Noise
- SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From
- Qwen3 Technical Report
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