arXiv:2505.12196v2 Announce Type: replace Abstract: The impressive linguistic abilities of large language models (LLMs) have recommended them as models of human sentence processing, with some conject...
The paper investigates the intrinsic dimension (ID) of large language model (LLM) representations as an indicator of linguistic complexity. By comparing ID across model layers for coordination vs. subordination, right‑branching vs. center‑embedding, and unambiguous vs. ambiguous attachment, the authors find consistent ID differences that align with established complexity contrasts. Experiments across six LLMs, including representational similarity and layer pruning analyses, confirm that more complex phenomena produce higher ID profiles, with peaks occurring at different layers for each contrast.
The study investigates whether large language models (LLMs) can generate mentalization profiles that are structurally coherent with mentalization‑based treatment (MBT) dimensions. Fifty GPT‑4.1 dialogues were produced, and the resulting narrative profiles were rated by five MBT‑trained psychiatrists on evaluative and argumentative coherence across canonical MBT axes and higher‑order dimensions. Ratings showed moderate‑to‑high structural coherence (mean scores 3.63–3.98) with strong interrater reliability (ICC(3,k) 0.60–0.84) and a strong association between evaluative and argumentative coherence (Pearson r 0.826–0.967). A negative control confirmed the specificity of the ratings, and clinicians noted that the outputs were linguistically organized and clinically interpretable, though lacking affective variability and contextual integration.
arXiv:2605. 00025v3 Announce Type: replace-cross Abstract: Speech neuroprosthesis systems decode intended speech from neural activity in the absence of audible output, offering a path to restoring communication for individuals with speech-impairing conditions.
arXiv:2607.21574v2 Announce Type: replace Abstract: Surprisal theory holds that the human processing difficulty of a linguistic unit in context is an affine function of its surprisal under some langu...
The study examined whether brain-language model alignment reflects shared computational mechanisms or merely stable lexical‑semantic correspondences. Using whole‑brain encoding across Mandarin, English, and French, transformer representations predicted activity in a distributed network that overlapped across languages and remained stable across layers. Contextual embeddings and measures of prediction or compression did not outperform static lexical embeddings, suggesting that alignment is robust but not informative about shared computational processes.
The study introduces a scalable acoustic‑masking method to quantify how much each consonant contributes to word intelligibility. By silencing individual consonants in isolated words and measuring misrecognition rates with three ASR models, the authors define a mask‑induced misrecognition rate (MMR). Across English, Spanish, German, and Czech, MMR negatively correlates with phoneme frequency and positively with functional load, revealing that consonant importance varies by language.
arXiv:2603.04317v2 Announce Type: replace-cross Abstract: A growing literature shows that variables can be linearly decoded from the activations of large language models (LLMs). These range from prop...
The paper studies how transformer representations evolve across layers by examining the intrinsic dimensionality (ID) of token embeddings and their neighborhood structures. It finds that closed‑class tokens expand and collapse earlier than open‑class tokens, and that these changes are linked to shifts in local geometry. The authors compare encoder and decoder models, showing distinct layer‑wise behaviors, and demonstrate that geometric features alone can predict a token’s part‑of‑speech and reveal how semantic content changes across layers.
arXiv:2608.22452v1 Announce Type: new Abstract: Surprisal, the negative log-probability a language model assigns to a word given its preceding context, reliably predicts adult reading times. Does it...
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:2603.04419v3 Announce Type: replace-cross Abstract: Vision-language models produce different object and use descriptions under different persona prompts, but low overlap alone does not identify...