Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study
cs.LG, cs.AI
Submitted: 2026-07-06
Updated: 2026-11-13
Code: https://github.com/otanl/microground
Terminology
Sources
- Transformers generalize differently from information stored in context vs in weights
- The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers
- Toy Models of Superposition
- How do Language Models Bind Entities in Context?
- On the Binding Problem in Artificial Neural Networks
- Compact Proofs of Model Performance via Mechanistic Interpretability
- Case-Based or Rule-Based: How Do Transformers Do the Math?
- The Impact of Positional Encoding on Length Generalization in Transformers
- Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
- Tracr: Compiled Transformers as a Laboratory for Interpretability
- Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?
- Progress measures for grokking via mechanistic interpretability
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- The Mechanistic Emergence of Symbol Grounding in Language Models
- The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis