Mechanistic Circuit Identification for Controllable Data Generation

arXiv:2608.24065 · cs.LG, cs.AI, cs.CL · Submitted 2026-08-25 · Read on arXiv

cs.LG, cs.AI, cs.CL

Submitted: 2026-08-25

Updated: 2026-08-25

Comments: 21 pages, 8 figures

Code: https://github.com/hannamw/eap-ig

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Steering — 49× in this paper · explained in 2 episodes
• Alignment — 20× in this paper · explained in 1 episode
• Ablation — 15× in this paper · explained in 1 episode
• Fine-Tuning — 15× in this paper · explained in 5 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Activation Addition — 8× in this paper · explained in 1 episode
• Calibration — 8× in this paper · explained in 7 episodes
• Interpretability — 8× in this paper · explained in 15 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Stage-Aware Mechanistic Scheduling — 5× in this paper
• Transformer — 5× in this paper · explained in 2 episodes
• Instruction Tuning — 4× in this paper · explained in 2 episodes
• Synthetic Data Generation — 4× in this paper · explained in 5 episodes
• Circuit Performance Ratio — 3× in this paper
• Consistency — 3× in this paper · explained in 3 episodes
• Core — 3× in this paper · explained in 2 episodes
• Pruning — 3× in this paper · explained in 4 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Area Under the Margin — 2× in this paper
• Embeddings — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Representation Engineering — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Data Pruning — 1× in this paper · explained in 2 episodes
• Graph Construction — 1× in this paper · explained in 3 episodes
• Lexical Diversity — 1× in this paper · explained in 2 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

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