# OrthoFormer: Instrumental Variable Estimation in Transformer Hidden States via Neural Control Functions

arXiv: https://arxiv.org/abs/2603.07431 · HTML: https://mlsanity.com/paper/2603.07431/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 8 Mar 2026.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Causal Transformer for Estimating Counterfactual Outcomes](https://mlsanity.com/paper/2204.07258/) (2022)
- [Adversarial Generalized Method of Moments](https://mlsanity.com/paper/1803.07164/) (2018)

## Abstract (arXiv)

Transformer architectures excel at sequential modeling yet remain fundamentally limited by correlational learning - they capture spurious associations induced by latent confounders rather than invariant causal mechanisms. We identify this as an epistemological challenge: standard Transformers conflate static background factors (intrinsic identity, style, context) with dynamic causal flows (state evolution, mechanism), leading to catastrophic out-of-distribution failure. We propose OrthoFormer, a causally grounded architecture that embeds instrumental variable estimation directly into Transformer blocks via neural control functions. Our framework rests on four theoretical pillars: Structural Directionality (time-arrow enforcement), Representation Orthogonality (latent-noise separation), Causal Sparsity (Markov Blanket approximation), and End-to-End Consistency (gradient- detached stage separation). We prove that OrthoFormer achieves bias strictly less than OLS for any valid instrument lag, with residual bias decaying geometrically as O(rhok ). We characterize the bias-variance-exogeneity trilemma inherent in self-instrumenting and identify the neural forbidden regression - where removing gradient detachment improves prediction loss while destroying causal validity. Experiments confirm all theoretical predictions. OrthoFormer represents a paradigm shift from correlational to causal sequence modeling, with implications for robustness, interpretability, and reliable decision-making under distribution shift.