# On the Limitations and Capabilities of Position Embeddings for Length Generalization

arXiv: https://arxiv.org/abs/2510.04130 · HTML: https://mlsanity.com/paper/2510.04130/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [The Impact of Positional Encoding on Length Generalization in Transformers](https://mlsanity.com/paper/2305.19466/) (2023)
- [Deep learning: a statistical viewpoint](https://mlsanity.com/paper/2103.09177/) (2021)
- [Exploring Length Generalization in Large Language Models](https://mlsanity.com/paper/2207.04901/) (2022)
- [What Algorithms can Transformers Learn? A Study in Length Generalization](https://mlsanity.com/paper/2310.16028/) (2023)
- [LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models](https://mlsanity.com/paper/2308.16137/) (2023)
- [Transformers Can Achieve Length Generalization But Not Robustly](https://mlsanity.com/paper/2402.09371/) (2024)
- [Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking](https://mlsanity.com/paper/2311.18817/) (2023)
- [Transformers Can Do Arithmetic with the Right Embeddings](https://mlsanity.com/paper/2405.17399/) (2024)
- [Why are Sensitive Functions Hard for Transformers?](https://mlsanity.com/paper/2402.09963/) (2024)
- [Generalization on the Unseen, Logic Reasoning and Degree Curriculum](https://mlsanity.com/paper/2301.13105/) (2023)
- [What is Wrong with Perplexity for Long-context Language Modeling?](https://mlsanity.com/paper/2410.23771/) (2024)
- [Length Generalization in Arithmetic Transformers](https://mlsanity.com/paper/2306.15400/) (2023)
- [A Formal Framework for Understanding Length Generalization in Transformers](https://mlsanity.com/paper/2410.02140/) (2024)
- [Neural Redshift: Random Networks are not Random Functions](https://mlsanity.com/paper/2403.02241/) (2024)
- [Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation](https://mlsanity.com/paper/2401.16421/) (2024)
- [Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure](https://mlsanity.com/paper/2405.20671/) (2024)
- [LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models](https://mlsanity.com/paper/2409.00509/) (2024)
- [Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalization](https://mlsanity.com/paper/2410.08898/) (2024)

## Abstract (arXiv)

In Transformers, Position Embeddings (PEs) significantly influence Length Generalization (LG) performance, yet their fundamental role remains unclear. In this work, we investigate the limitations and capabilities of PEs in achieving LG. We theoretically analyze PEs in Position-Only Linear Attentions (POLAs), introducing Linear Representation Complexity (LRC) to characterize when PEs enable LG. Our analysis shows that PEs do not expand computational capabilities but structure learned computations across positions. Extending to practical Transformers, we propose Sequential Representation Complexity (SRC) and conjecture that LG is possible if and only if SRC remains invariant across scales. We support this hypothesis with empirical evidence in various reasoning tasks. To enhance LG, we introduce Scale Hint, allowing flexible instance scaling, and a Learning-Based Position Embedding framework that automatically learns positional relations. Our work provides theoretical insights and practical strategies for improving LG in Transformers.