Team Aurevia introduces a local open-weight healthcare NLP system for the CLPsych 2026 Shared Task, predicting MIND-coded self-state elements, moments of change, summaries, anddynamic signatures from social media timelines. The task is difficult because coarse presence, fine-grained ABCD subelements, and timeline-level change require different longitudinal evidence over privacy-sensitive mental-health language. Our system combines TF-IDF retrieval, schema-constrained local Qwen2.5 prompting, ordinal calibration, and conservative post-processing. Among official runs, Aurevia ranked 3rd of 17 for Task 1.2 presence prediction, 5th of 13 overall for Task 3.1, 1st on Task 3.1 consistency, and 2nd of 9 for MIND-coded deterioration signatures, showing that constrained local LLM pipelines can remain competitive in sensitive healthcare NLP while reducing reliance on hosted proprietary inference.

Large language models (LLMs) have emerged as a candidate ‘model organism’ for human language, offering an unprecedented opportunity to study the computational basis of linguistic disorders like aphasia. However, traditional clinical assessments are ill-suited for LLMs, as they presuppose human-like pragmatic pressures and probe cognitive processes not inherent to artificial architectures. We introduce the Text Aphasia Battery (TAB), a text-only benchmark adapted from the Quick Aphasia Battery (QAB) to assess aphasic-like deficits in LLMs. The TAB comprises four subtests: Connected Text, Word Comprehension, Sentence Comprehension, and Repetition. This paper details the TAB’s design, subtests, and scoring criteria. To facilitate large-scale use, we validate an automated evaluation protocol using Gemini 2.5 Flash, which achieves reliability comparable to expert human raters (prevalence-weighted Cohen’s k=0.255 for model–consensus agreement vs. 0.286 for human–human agreement). We release TAB as a clinically-grounded, scalable framework for analyzing language deficits in artificial systems.

Human listeners readily adjust to unfamiliar speakers and language varieties through exposure, but do these adaptation benefits extend to state-of-the-art spoken language models (SLMs)? We introduce a scalable framework that allows for in-context learning (ICL) in Phi-4 Multimodal (Phi-4-MM) using interleaved task prompts and audio-text pairs, and find that as few as 12 example utterances (~50 seconds) at inference time reduce word error rates by a relative 19.7% (1.2 pp.) on average across diverse English corpora. These improvements are most pronounced in low-resource varieties, when the context and target speaker match, and when more examples are provided—though scaling our procedure yields diminishing marginal returns to context length. Overall, we find that our novel ICL adaptation scheme (1) reveals a similar performance profile to human listeners, and (2) demonstrates consistent improvements to automatic speech recognition (ASR) robustness across diverse speakers and language backgrounds. While adaptation succeeds broadly, significant gaps remain for certain varieties, revealing where current models still fall short of human flexibility. We release our prompts and code on GitHub.

We introduce a novel fine-tuning approach that effectively primes transformer-based language models to detect rhetorical and psychological techniques within internet memes. Our end-to-end system retains multilingual and task-general capacities from pretraining stages while adapting to domain intricacies using an increasingly targeted set of examples– achieving competitive rankings across English, Bulgarian, and North Macedonian. We find that our monolingual post-training regimen is sufficient to improve task performance in 17 language varieties beyond equivalent zero-shot capabilities despite English-only data. To promote further research, we release our code publicly on GitHub.

This study investigates the clustering of words into Part-of-Speech (POS) classes in Kolyma Yukaghir. In grammatical descriptions, lexical items are assigned to POS classes based on their morphological paradigms. Discursively, however, these classes share a fair amount of morphology. In this study, we turn to POS induction to evaluate if classes based on quantification of the distributions in which roots and affixes are used can be useful for language description purposes, and, if so, what those classes might be. We qualitatively compare clusters of roots and affixes based on four different definitions of their distributions. The results show that clustering is more reliable for words that typically bear more morphology. Additionally, the results suggest that the number of POS classes in Kolyma Yukaghir might be smaller than stated in current descriptions. This study thus demonstrates how unsupervised learning methods can provide insights for language description, particularly for highly inflectional languages.

We develop and probe a model for detecting the boundaries of prosodic chunks in untranscribed conversational English speech. The model is obtained by fine-tuning a Transformer-based speech-to-text (STT) model to integrate the identification of Intonation Unit (IU) boundaries with the STT task. The model shows robust performance, both on held-out data and on out-of-distribution data representing different dialects and transcription protocols. By evaluating the model on degraded speech data, and comparing it with alternatives, we establish that it relies heavily on lexico-syntactic information inferred from audio, and not solely on acoustic information typically understood to cue prosodic structure. We release our model as both a transcription tool and a baseline for further improvements in prosodic segmentation.