# A Theoretical Framework for OOD Robustness in Transformers using Gevrey Classes

arXiv: https://arxiv.org/abs/2504.12991 · HTML: https://mlsanity.com/paper/2504.12991/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 50 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Builds on (most cited first, 30 of 39)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change](https://mlsanity.com/paper/1605.09096/) (2016)
- [Learning with a Wasserstein Loss](https://mlsanity.com/paper/1506.05439/) (2015)
- [Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation](https://mlsanity.com/paper/1705.08475/) (2017)
- [What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization](https://mlsanity.com/paper/2305.19420/) (2023)
- [Theoretical Analysis of Domain Adaptation with Optimal Transport](https://mlsanity.com/paper/1610.04420/) (2016)
- [Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations](https://mlsanity.com/paper/2306.04618/) (2023)
- [Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages](https://mlsanity.com/paper/2310.14799/) (2023)
- [GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective](https://mlsanity.com/paper/2211.08073/) (2022)
- [Universal Representation Learning from Multiple Domains for Few-shot Classification](https://mlsanity.com/paper/2103.13841/) (2021)
- [Transformers Provably Solve Parity Efficiently with Chain of Thought](https://mlsanity.com/paper/2410.08633/) (2024)
- [LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning](https://mlsanity.com/paper/2101.06223/) (2021)
- [Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods](https://mlsanity.com/paper/2408.14511/) (2024)
- [Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure](https://mlsanity.com/paper/2405.20671/) (2024)
- [Can In-context Learning Really Generalize to Out-of-distribution Tasks?](https://mlsanity.com/paper/2410.09695/) (2024)

## Built on by (most cited first, 4 of 4)

- [Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens](https://mlsanity.com/paper/2508.01191/) (2025)
- [Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies](https://mlsanity.com/paper/2602.01816/) (2026)
- [Can GRPO Help LLMs Transcend Their Pretraining Origin?](https://mlsanity.com/paper/2510.15990/) (2025)
- [On the Out-of-Distribution Generalization of Reasoning in Multimodal LLMs for Simple Visual Planning Tasks](https://mlsanity.com/paper/2602.15460/) (2026)

## Abstract (arXiv)

We study the robustness of Transformer language models under semantic out-of-distribution (OOD) shifts, where training and test data lie in disjoint latent spaces. Using Wasserstein-1 distance and Gevrey-class smoothness, we derive sub-exponential upper bounds on prediction error. Our theoretical framework explains how smoothness governs generalization under distributional drift. We validate these findings through controlled experiments on arithmetic and Chain-of-Thought tasks with latent permutations and scalings. Results show empirical degradation aligns with our bounds, highlighting the geometric and functional principles underlying OOD generalization in Transformers.