mlsanityData to 14 Oct 2026

Jordan-RoPE: Non-Semisimple Relative Positional Encoding via Complex Jordan Blocks

arXiv 2605.04217 ↗First posted 5 May 2026cs.LG cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Relative positional encodings determine which functions of query-key lag can enter the primitive attention logit. RoPE supplies a rotary phase, while ALiBi supplies an additive distance bias. Motivated by group-theoretic views of linear translation-invariant positional encodings, we study a non-semisimple case in which a complex rotary eigenvalue and a nilpotent response live in the same defective Jordan block. The resulting relative operator generates oscillatory-polynomial features such as e-γ dcos(ω d), e-γ dsin(ω d), d e-γ dcos(ω d), and d e-γ dsin(ω d), for causal lag d=i-j≥ 0. Thus the construction realizes a distance-modulated phase basis d eiω d, rather than merely adding a separate distance channel to RoPE. We formulate Exact Jordan-RoPE as a non-semisimple one-parameter representation, give its real block form, and specify the contragredient query action required by non-orthogonal positional maps. We also distinguish this exact representation from stabilized variants whose bounded shear improves numerical behavior but breaks the exact group law. Kernel-level diagnostics and a Jordan-friendly synthetic language-model task show that the coupled Jordan basis is useful when the target contains distance-modulated phase interactions. On a small WikiText-103 byte language model, a scaled-exact variant improves over RoPE and direct-sum baselines within the Jordan family, while RoPE+ALiBi remains strongest overall. The evidence is structural rather than a broad performance claim.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 31 references that are in the map. First posted on arXiv 5 May 2026.

Builds on

26 of 31 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  3. 2016Pointer Sentinel Mixture Modelscited by 3,096
  4. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  5. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  6. 2018Self-Attention with Relative Position Representationscited by 1,120
  7. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  8. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 740
  9. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
  10. 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 601
  11. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 393
  12. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 350
14 more
  1. 2023The Impact of Positional Encoding on Length Generalization in Transformerscited by 327
  2. 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokenscited by 313
  3. 2018Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Datasetcited by 217
  4. 2018Music Transformercited by 211
  5. 2016FMA: A Dataset For Music Analysiscited by 207
  6. 2022A Length-Extrapolatable Transformercited by 127
  7. 2022How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projectionscited by 122
  8. 2022KERPLE: Kernelized Relative Positional Embedding for Length Extrapolationcited by 86
  9. 2016Learning Features of Music from Scratchcited by 58
  10. 2023Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvaluescited by 36
  11. 2024LieRE: Lie Rotational Positional Encodingscited by 18
  12. 2023Algebraic Positional Encodingscited by 10
  13. 2024Provable Benefits of Complex Parameterizations for Structured State Space Modelscited by 9
  14. 2025Group Representational Position Encodingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.