arXiv:2608. 12717v1 Announce Type: new Abstract: Mechanistic interpretability of large language models lacks spatially resolved, falsifiable tools for testing whether internal components are specialized for distinct cognitive operations.
arXiv:2608. 06429v1 Announce Type: cross Abstract: Interpretability methods for large language models (LLMs) describe internal state but do not directly test whether that state is causally sufficient to produce the observed behavior.
arXiv:2607. 11621v1 Announce Type: new Abstract: Aphasia following stroke commonly produces systematic naming errors with characteristic profiles, but whether general-purpose language models not designed for clinical simulation can reproduce these patterns remains untested.
The study investigates whether language models tailored to specific cognitive domains better align with corresponding brain systems. By prompting and fine‑tuning large language models into six domain experts—sensory, spatial, numerical, reasoning, social, and abstract—the authors find that each expert’s representations more closely match the brain region associated with its domain than other experts. This domain‑specific alignment holds across multiple base models and fMRI datasets, while overall prediction accuracy remains largely unchanged, indicating that regional alignment can be obscured when summarizing across the brain.
arXiv:2606. 05206v1 Announce Type: cross Abstract: Fragmentation is common in interdisciplinary fields with diverse methods and theoretical commitments.
The paper investigates how the upper spectral tails of weight matrices in decoder‑only transformer language models influence reasoning behavior. By performing controlled interventions on the query–key product and comparing them to factor‑level surgeries, the authors find that edits targeting the spectral tail more strongly affect model performance across multiple checkpoints and reasoning benchmarks. The study also explores how inverse participation ratios predict accuracy transitions and shows that tail‑aware low‑rank adaptations converge faster than standard methods.
arXiv:2603. 28387v2 Announce Type: replace Abstract: Trustworthy clinical AI requires that performance gains reflect genuine evidence integration rather than surface-level artifacts.
arXiv:2605.01609v2 Announce Type: replace-cross Abstract: We find that transformer concept representations systematically anti-concentrate in the spectral tail of the unembedding covariance, encoding...
arXiv:2603.28387v3 Announce Type: replace-cross Abstract: Trustworthy clinical AI must use real evidence and avoid relying on surface-level artifacts. We evaluate 12 open-weight vision-language model...
arXiv:2607. 16325v1 Announce Type: cross Abstract: Foundation models provide powerful representations for brain MRI analysis, but their predictions remain difficult to interpret in anatomically meaningful terms.
MIRTO is an evaluation protocol for unsupervised anomaly segmentation in brain MRI that explicitly documents key methodological choices—such as registration alignment, threshold setting, and false‑positive budgeting—and measures their impact. It applies a registration check, uses validation data for thresholding, reports realized false‑positive volumes, and repeats each comparison across 15,552 evaluation pipelines with bootstrap intervals. In a study on four UAD methods and 312 BraTS 2020 subjects, MIRTO revealed that an axis‑order mismatch dramatically lowered a diffusion model’s voxel AUROC, and that many performance differences were driven by lesion definition and threshold transfer rather than model quality.
arXiv:2508.17171v3 Announce Type: replace Abstract: Imaging biomarkers in magnetic resonance imaging (MRI) are important tools for diagnosing, tracking and treating Alzheimer's disease (AD). Neurofib...
arXiv:2608.28714v1 Announce Type: cross Abstract: Objective: Deep learning accelerates brain MRI four- to tenfold, but models can erase lesions or synthesize false tissue - failures pixel-averaged me...