# RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding

arXiv: https://arxiv.org/abs/2609.10305 · HTML: https://mlsanity.com/paper/2609.10305/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 11 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [Hyperbolic Neural Networks](https://mlsanity.com/paper/1805.09112/) (2018)
- [Using the Output Embedding to Improve Language Models](https://mlsanity.com/paper/1608.05859/) (2016)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)

## Abstract (arXiv)

Language models under one million parameters matter for edge deployment, domain adaptation, and reproducible research, yet a two-layer LSTM or Transformer at embedding width d = 128 still spends roughly one third of its capacity on the output matrix W_out in R^(d x |V|). We propose Riemannian Language Models (RiLM), which remove that layer entirely: context unfolds as a trajectory on a Riemannian manifold, and next-token probabilities arise from squared geodesic distance between the current state and vocabulary embeddings. The same embedding map serves input and output -- decoding is geometry. We instantiate the framework on flat R^d (Flat RiLM) and the Poincare ball H^d (HypRiLM) with a shared MLP composition map phi (~290k parameters, d = 128, |V| = 2000). Across five seeds on WikiText-2, HypRiLM reaches 54.2 +/- 0.2 validation perplexity versus 87.6 +/- 0.6 for Flat RiLM; tied and matched LSTM, Transformer, and SSM controls remain at 113-147 PPL on WT-2 -- HypRiLM leads by roughly 2x over the strongest tied recurrent baseline (SSM, 113.0 +/- 3.8). Penn Treebank and a 10k-vocabulary stress test confirm that geodesic decoding transfers across corpora and larger |V|, while hyperbolic curvature helps selectively. We also characterize boundary collapse in naive hyperbolic recurrence and show how Mobius stabilization restores trainability. Claims are scoped to controlled small-model comparisons, not full-vocabulary state of the art.