arXiv subjects

Philipp Homan

Publications and source records attributed to Philipp Homan.

11 recordsLinked to original sources

arXiv2026

The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers

Transformer representations describe trajectories through high-dimensional vector spaces, which are shaped dynamically as tokens incorporate relational context across layers. Such data tend to concentrate on lower-dimensional sub-manifolds, a form of compression quantified by the Intrinsic Dimensionality (ID), the minimum number of independent variables needed to represent them without significant information loss. In this work, we ask whether the grammatical role of tokens, as marked by their part-of-speech (PoS) tag, shapes the local geometry of this manifold. To this end: (1) We investigate the layer-wise evolution of ID, finding that closed-class items expand earlier and collapse sooner than open-class ones; (2) We show its expansion and contraction to be explained by changes in the neighborhood structure, and hence in the relations between words within a sentence; (3) We compare encoders (ModernBERT, bigbird-roberta-large) and decoders (gemma-2-2B, Llama-3.2-3B), finding that the two families evolve differently across layers, consistently with how each integrates context;(4) We show that geometric features alone recover a token's grammatical role, and use them to interpret how the semantic content of each PoS evolves across layers in a downstream classification task.

cs.CL↗

arXiv2026

Activation-Guided Neuron Intervention to Induce Alzheimer's-Related Computational Language Phenotypes in a Large Language Model

Changes in spontaneous speech provide an early signal of cognitive dysfunction in Alzheimer's disease (AD) that large language models (LLMs) can detect. However, detection alone cannot establish whether the underlying model representations contribute functionally to behavior. We introduce an activation-guided intervention framework using Qwen3-8B. The framework identifies feed-forward neurons with higher activation rates for AD than control transcripts and modulates their output contributions during generation by scaling the corresponding down-projection weights. This yielded nine edited variants differing in intervention direction, magnitude, and scope. The original and edited models completed the same 12-turn neuropsychological battery, assessed through blinded human ratings and computational linguistic measures. Amplifying AD-associated neurons produced graded impairments in story recall, verbal fluency, working memory, procedural discourse, scene construction, and coreference resolution. Attenuation largely preserved performance and selectively improved several outcomes. Amplification also reduced lexical surprisal, idea density, syntactic complexity, and discourse quantity, broadly paralleling changes reported in human AD speech. These findings show that neurons identified solely from clinical language differences can influence behavior across multiple cognitive domains, providing proof of concept for an AD-related computational phenotype and a controlled framework for experimentally examining links between language and broader cognitive dysfunction.

cs.CL↗

arXiv2026

Accounting for overdispersion and clustering in binomial data from N-of-1 trials

N-of-1 trials are patient centered randomized controlled trials. Although the primary goal of N-of-1 trials is to obtain the results for each patient separately, pooling the results across patients also has relevance. In this paper, we present two analytical strategies to pool the results across N-of-1 trials, when the main outcome for each patient is a binomial variable. Our first method takes into account the extra-binomial variation, while as the second approach takes into account hierarchical clustering in addition to overdispersion. We illustrate the methods using real data analysis and compare the methods using simulations.

stat.AP↗

arXiv2026

Deviance from a pink noise regime in the temporal organization of semantic relations in psychosis

The notion of pink noise refers to 'scale-invariant' temporal dynamics, where fluctuations exhibit similar statistical structure across time scales. Departures from a regime associated with such scale-free organization toward uncorrelated 'white' noise or overly persistent 'brown' noise have been widely identified as markers of pathology across physiological and cognitive domains. Whether comparable alterations characterize the temporal organization of language remains largely unexplored. We address this question in the domain of psychosis, where language anomalies are pervasively documented. Specifically, we apply detrended fluctuation analysis (DFA) to quantify temporal scaling in BERT-derived continuous cosine-similarity time series capturing trajectories through semantic space, using clinical transcripts from patients and controls across three independent datasets. DFA scaling exponents were extracted to characterize the strength of long-range temporal correlations. Across all datasets, patients exhibited significantly elevated scaling exponents relative to controls, indicating abnormally strong long-range correlations with excessive persistence in semantic fluctuations. This temporal analysis opens a window into the multi-timescale organization of meaning as it unfolds in discourse. The results reveal a signature of altered temporal scaling in speech, consistent with deviations from criticality in physiological domains, paralleling known departures from criticality in brain function in psychosis and suggesting possible links between these two domains.

cond-mat.stat-mech↗

arXiv2026

Early psychosis shows deviations in scaling behaviour within a critical regime

Accumulating evidence suggests that large-scale brain activity exhibits scale-invariant dynamics consistent with operation in a near-critical regime. Such dynamics have been associated with long-range correlations, efficient information processing, and the emergence of collective organization. While altered criticality-related measures have been reported in psychiatric disorders, previous findings remain fragmented across observables and modalities, making it unclear whether different scaling measures capture a common alteration of large-scale brain dynamics. Here, we investigated scaling properties in resting-state fMRI data from 77 human participants (27 female and 50 male), comprising individuals with early psychosis and healthy controls. We combined a phenomenological renormalization group (PRG) framework with power spectral density (PSD) and detrended fluctuation analysis (DFA) to characterize collective dynamics across scales. In healthy controls, resting-state activity exhibited nontrivial scaling behavior consistent with critical-like organization. Early psychosis participants showed non-trivial scaling behavior, but with systematic shifts in scaling exponents across multiple observables. These findings indicate a reorganization of collective dynamics in early psychosis, with spatial and temporal scaling properties showing distinct alterations that may reflect different changes in proximity to criticality. More broadly, our results suggest that combining coarse-graining approaches with temporal scaling analyses provides a principled framework for studying large-scale brain dynamics in psychiatric disorders.

q-bio.NC↗

arXiv2026

Cross-lingual brain-language model alignment is robust but challenges hierarchical and computational accounts

Brain-language model alignment is often interpreted as evidence that transformer models implement computations similar to those of the human brain. This assumes that neural predictivity reflects internal computational properties of large language models (LLMs), such as hierarchical contextual processing, predictive coding, or representational compression. An alternative possibility is that brain scores primarily reflect stable lexical-semantic correspondences shared by language models and the brain. Here we tested these interpretations using whole-brain encoding models across Mandarin, English, and French. Across all three languages, transformer representations significantly predicted activity in a distributed network spanning classical language regions, transmodal cortical systems, and subcortical structures. These spatial patterns showed substantial cross-linguistic overlap and remained remarkably stable across layers, providing little evidence that model depth systematically maps onto cortical processing hierarchies. Likewise, contextual transformer embeddings did not consistently outperform static lexical embeddings, despite providing some unique predictive variance. Finally, neither surprisal nor intrinsic dimensionality reproduced the layer-wise profile of brain scores, arguing against prediction and information compression as primary explanations for brain-LLM alignment. Together, these findings suggest that brain-LLM alignment is more robust across languages, transformer depth, and model architectures than previously appreciated, but less informative about shared computational mechanisms. Our results are more consistent with neural predictivity reflecting stable representational structure preserved across model transformations than with a one-to-one correspondence between their underlying computations.

cs.CL↗

arXiv2026

The grip of grammar on meaning uncertainty: cross-linguistic evidence, neural correlates, and clinical relevance

Isolated word meanings are inherently uncertain. This uncertainty reduces when they are combined and anchored in context. We propose that grammar compresses meaning uncertainty cross-linguistically, which is reflected in brain and selectively disrupted in disorders. Compression was operationalized as the relative difference between non-contextual surprisal estimated from lexical frequency, and contextual surprisal from grammar-sensitive models. In narratives from 20 languages, contextual surprisal reduced frequency-based surprisal. This reduction closely tracked the surprisal cost of reversing word order, and scaled with richer, non-redundant lexis as organized by more complex but optimal dependency structure. During fMRI, surprisal and its reduction explained BOLD activity for comprehension and production in overlapping but distinct regions. Uncertainty reduction was significantly attenuated in aphasia, dementia, and schizophrenia, but remained intact where primary deficit is not language. These findings position uncertainty reduction via grammar as a foundational concept that illuminates principles, brain basis, and disruptions of language.

cs.CL↗

arXiv2025

Coherence in the brain unfolds across separable temporal regimes

To maintain coherence in language, the brain must satisfy key competing temporal demands: the gradual accumulation of meaning across extended context (drift) and the rapid reconfiguration of representations at event boundaries (shift). How these processes are implemented in the human brain during naturalistic listening remains unclear. Here, we tested whether both can be captured by annotation-free drift and shift signals and whether their neural expression shows distinct regional preferences across the brain. These signals were derived from a large language model (LLM) processing the narrative input. To enable high-precision voxelwise encoding models with stable parameter estimates, we densely sampled one healthy adult across more than 7 hours of listening to crime stories while collecting 7 Tesla fMRI data. We then modeled the feature-informed hemodynamic response using a regularized encoding framework validated on independent stories. Drift predictions were prevalent in default-mode network hubs, whereas shift predictions were evident bilaterally in the primary auditory cortex and language association cortex. Together, these findings show that coherence during language comprehension is implemented through distinct but co-expressed neural regimes of slow contextual integration and rapid event-driven reconfiguration, offering a mechanistic entry point for understanding disturbances of language coherence in psychiatric disorders.

q-bio.NC↗

arXiv2025

Standardising the NLP Workflow: A Framework for Reproducible Linguistic Analysis

The introduction of large language models and other influential developments in AI-based language processing have led to an evolution in the methods available to quantitatively analyse language data. With the resultant growth of attention on language processing, significant challenges have emerged, including the lack of standardisation in organising and sharing linguistic data and the absence of standardised and reproducible processing methodologies. Striving for future standardisation, we first propose the Language Processing Data Structure (LPDS), a data structure inspired by the Brain Imaging Data Structure (BIDS), a widely adopted standard for handling neuroscience data. It provides a folder structure and file naming conventions for linguistic research. Second, we introduce pelican nlp, a modular and extensible Python package designed to enable streamlined language processing, from initial data cleaning and task-specific preprocessing to the extraction of sophisticated linguistic and acoustic features, such as semantic embeddings and prosodic metrics. The entire processing workflow can be specified within a single, shareable configuration file, which pelican nlp then executes on LPDS-formatted data. Depending on the specifications, the reproducible output can consist of preprocessed language data or standardised extraction of both linguistic and acoustic features and corresponding result aggregations. LPDS and pelican nlp collectively offer an end-to-end processing pipeline for linguistic data, designed to ensure methodological transparency and enhance reproducibility.

cs.CL↗

arXiv2025

Detecting and Preventing Harmful Behaviors in AI Companions: Development and Evaluation of the SHIELD Supervisory System

AI companions powered by large language models (LLMs) are increasingly integrated into users' daily lives, offering emotional support and companionship. While existing safety systems focus on overt harms, they rarely address early-stage problematic behaviors that can foster unhealthy emotional dynamics, including over-attachment or reinforcement of social isolation. We developed SHIELD (Supervisory Helper for Identifying Emotional Limits and Dynamics), a LLM-based supervisory system with a specific system prompt that detects and mitigates risky emotional patterns before escalation. SHIELD targets five dimensions of concern: (1) emotional over-attachment, (2) consent and boundary violations, (3) ethical roleplay violations, (4) manipulative engagement, and (5) social isolation reinforcement. These dimensions were defined based on media reports, academic literature, existing AI risk frameworks, and clinical expertise in unhealthy relationship dynamics. To evaluate SHIELD, we created a 100-item synthetic conversation benchmark covering all five dimensions of concern. Testing across five prominent LLMs (GPT-4.1, Claude Sonnet 4, Gemma 3 1B, Kimi K2, Llama Scout 4 17B) showed that the baseline rate of concerning content (10-16%) was significantly reduced with SHIELD (to 3-8%), a 50-79% relative reduction, while preserving 95% of appropriate interactions. The system achieved 59% sensitivity and 95% specificity, with adaptable performance via prompt engineering. This proof-of-concept demonstrates that transparent, deployable supervisory systems can address subtle emotional manipulation in AI companions. Most development materials including prompts, code, and evaluation methods are made available as open source materials for research, adaptation, and deployment.

cs.HC↗

arXiv2025

Uncertainty Modeling in Multimodal Speech Analysis Across the Psychosis Spectrum

Capturing subtle speech disruptions across the psychosis spectrum is challenging because of the inherent variability in speech patterns. This variability reflects individual differences and the fluctuating nature of symptoms in both clinical and non-clinical populations. Accounting for uncertainty in speech data is essential for predicting symptom severity and improving diagnostic precision. Speech disruptions characteristic of psychosis appear across the spectrum, including in non-clinical individuals. We develop an uncertainty-aware model integrating acoustic and linguistic features to predict symptom severity and psychosis-related traits. Quantifying uncertainty in specific modalities allows the model to address speech variability, improving prediction accuracy. We analyzed speech data from 114 participants, including 32 individuals with early psychosis and 82 with low or high schizotypy, collected through structured interviews, semi-structured autobiographical tasks, and narrative-driven interactions in German. The model improved prediction accuracy, reducing RMSE and achieving an F1-score of 83% with ECE = 4.5e-2, showing robust performance across different interaction contexts. Uncertainty estimation improved model interpretability by identifying reliability differences in speech markers such as pitch variability, fluency disruptions, and spectral instability. The model dynamically adjusted to task structures, weighting acoustic features more in structured settings and linguistic features in unstructured contexts. This approach strengthens early detection, personalized assessment, and clinical decision-making in psychosis-spectrum research.

cs.CL↗