arXiv:2607. 07047v1 Announce Type: cross Abstract: Understanding the geometric structure of pre-trained language model embeddings matters for interpretability and safety.
arXiv:2602. 15029v3 Announce Type: replace Abstract: The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a circle, historical years form a smooth one-dimensional manifold, and cities' latitudes and longitudes can be decoded using a linear probe.
Neural Collapse predicts that balanced one-hot classification pushes model representations to be equally far from each other; a symmetric configuration that depends only on the output label and ignores any semantic similarity in the inputs. This creates a puzzle: next-token prediction language models are trained predominantly (as context length increases) with one-hot labels: the same context is very unlikely to appear twice in training with different labels.
arXiv:2605. 24942v2 Announce Type: replace-cross Abstract: Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation to nonlinear methods such as angular and kernelized steering, which define intervention transformations without learning an explicit geometry over paths in activation space.
arXiv:2604. 20817v2 Announce Type: replace-cross Abstract: Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$.
arXiv:2606. 26749v1 Announce Type: new Abstract: Neural Collapse predicts that balanced one-hot classification pushes model representations to be equally far from each other; a symmetric configuration that depends only on the output label and ignores any semantic similarity in the inputs.
arXiv:2606. 05173v1 Announce Type: cross Abstract: Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are strongly anchored to surface-form token identity rather than deeper semantic structure.
arXiv:2607. 13660v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) representations form a semantic embedding space governed by cosine similarity, reflecting an intrinsic hyperspherical geometry.
arXiv:2602. 07739v2 Announce Type: replace-cross Abstract: Embedding geometry plays a fundamental role in retrieval quality, yet dense retrievers for retrieval-augmented generation (RAG) remain largely confined to Euclidean space.
arXiv:2602. 01893v2 Announce Type: replace-cross Abstract: We present a geometric framework for analysing multi-head attention in large language models (LLMs).
arXiv:2605. 28854v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit remarkable flexibility in adapting to novel tasks from in-context examples without parameter updates, a capability known as in-context learning (ICL).
arXiv:2607. 17770v1 Announce Type: cross Abstract: Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations.
arXiv:2511. 11041v2 Announce Type: replace-cross Abstract: We find that current sentence-embedding models produce outputs with a consistent bias: every embedding $e$ decomposes as $\tilde e + \mu$, where the mean $\mu$ is near-identical across all sentences.