In-Context Learning Amplifies a Latent Symbolic Circuit

arXiv:2609.36265 · cs.LG, cs.AI, cs.CL · Submitted 2026-09-28 · Read on arXiv

cs.LG, cs.AI, cs.CL

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/melissawessel/icl-symbolic

Terminology

• Accuracy — 49× in this paper · explained in 1 episode
• In-Context Learning — 20× in this paper · explained in 4 episodes
• Core — 14× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Steering — 5× in this paper · explained in 2 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Activation Patching — 4× in this paper · explained in 2 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Generalization — 3× in this paper · explained in 13 episodes
• International Conference on Machine Learning — 3× in this paper
• Trace — 3× in this paper · explained in 2 episodes
• Symbolic Abstraction — 2× in this paper
• Symbolic Induction — 2× in this paper
• Activation Steering — 1× in this paper · explained in 4 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Mechanistic interpretability — 1× in this paper · explained in 2 episodes
• Representation Engineering — 1× in this paper · explained in 2 episodes

Sources

• The Llama 3 Herd of Models
• In-context Learning and Induction Heads
• Steering Language Models With Activation Engineering

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