The paper introduces task‑weighted charts, a method that defines low‑dimensional coordinate systems based on a chosen functional of a language model’s representation. Using these charts, the authors show that next‑token prediction requires 70–90% of the residual stream’s width to maintain perplexity, a width largely unused by variance‑based analyses. The study demonstrates that charts trained under the functional’s metric preserve predictions better than variance‑based or optimal linear compression when only a few dimensions are retained.
arXiv:2607. 14112v1 Announce Type: cross Abstract: Large language models (LLMs) are evaluated as though perfect reliability is achievable for any task given sufficient scale.
The paper argues that large language models cannot achieve perfect reliability for any task, even with unlimited scale. It establishes that each generative task has an inherent reliability ceiling set by how much output uncertainty can be resolved from observable context, with a resolvable part that can be improved by more context and a subjective part tied to task ambiguity. The authors derive a scaling law showing that performance is limited by the scarcer resource—either training data or model capacity—and explain how this law explains phenomena such as retrieval augmentation and catastrophic forgetting.
arXiv:2609.10305v1 Announce Type: new Abstract: Language models under one million parameters matter for edge deployment, domain adaptation, and reproducible research, yet a two-layer LSTM or Transfor...
arXiv:2608. 01624v1 Announce Type: cross Abstract: Adapting a language model to a task no longer requires training all of its weights, and a line of parameter-efficient methods has driven the trainable count from billions down to a handful of scalars.
arXiv:2608. 12447v1 Announce Type: new Abstract: Trained transformer models develop privileged bases: coordinate axes whose statistics differ from the rest of the residual stream.
arXiv:2603. 06592v2 Announce Type: replace-cross Abstract: Contemporary studies in mechanistic interpretability have uncovered many puzzling phenomena in the neural information processing of Transformer-based language models, such as induction heads, function vectors, and the Hydra effect.
arXiv:2606. 07559v2 Announce Type: replace-cross Abstract: Fine-tuning a language model often fails silently when its correct completion must outrank a near-synonym competitor.
arXiv:2608. 05238v1 Announce Type: new Abstract: Training multimodal models to align time series with language runs into a self-supervision trap.
The paper investigates how six naturalistic and synthetic input perturbations affect decoder‑only language models at three levels: output behavior, hidden‑state geometry, and attention‑head function. Using GPT‑2 and Qwen2.5 checkpoints, the authors analyze layerwise geometry with centered kernel alignment and intrinsic dimension, and examine attention‑head responses in GPT‑2. They find that perturbation types produce distinct metric profiles that are not fully captured by output measures and vary across checkpoints, highlighting the need for multi‑level evaluation of robustness.
arXiv:2607. 22757v1 Announce Type: cross Abstract: We introduce Graded Large Language Models (GLLMs), an algebraic framework that equips the representation space of a transformer with a grading and propagates the induced weighted scalar action through embeddings, self-attention, and the training objective.
arXiv:2606. 02765v1 Announce Type: cross Abstract: Model dimension ($d_{model}$) is a fundamental hyperparameter in transformer language models, yet its role in setting the geometric limits of feature representation remains under-explored.
arXiv:2602. 17743v2 Announce Type: replace Abstract: In-context learning (ICL) allows large language models to adapt to new tasks from a few examples without updating their parameters.