We provide an overview of the CLPsych 2026 Shared Task, which focuses on capturing and characterizing mental health dynamics from social media timelines through structured modeling of self-states. This year advances the longitudinal paradigm set by prior CLPsych shared tasks (2022, 2025), by integrating fine-grained psychological representation using the MIND framework. The task is organized into three main components: (1) post-level identification of adaptive and maladaptive self-states through ྀི elements and sub-elements, along with estimation of their presence; (2) timeline-level detection of Moments of Change, including both abrupt switches and gradual escalations based on ABCd element and sub-element combinations; and (3) sequence-level modeling, involving summarization of change processes over time and identification of recurrent dynamic signatures.

This system paper presents the approach of Team TONI-NLP to the PsyDefDetect 2026 shared task. The objective of the task was to classify utterances from helper–seeker conversations into nine categories: seven labels representing progressively higher levels of defensive maturity, one label indicating the absence of a defense mechanism, and one label for cases requiring additional information. We investigated several modern NLP approaches, including prompt engineering, fine-tuning, hierarchical modeling and classification using text embeddings derived from transformer-based models as well as classical embeddings such as TF-IDF. Our results show that ensemble methods performed best among our submitted systems, achieving a macro-F1 score of 0.320 and ranking 9th in the shared task out of 21 teams.

With the advent of modern Computational Linguistic techniques and the growing societal mental health crisis, we contribute to the field of Clinical Psychology by participating in the CLPsych 2025 shared task. This paper describes the methods and results obtained by the uOttawa team’s submission (which included a researcher from the National Institutes of Health in the USA, in addition to three researchers from the University of Ottawa, Canada). The task consists of four subtasks focused on modeling longitudinal changes in social media users’ mental states and generating accurate summaries of these dynamic self-states. Through prompt engineering of a modern large language model (Llama-3.3-70B-Instruct), the uOttawa team placed first, sixth, fifth, and second, respectively, for each subtask, amongst the other submissions. This work demonstrates the capacity of modern large language models to recognize nuances in the analysis of mental states and to generate summaries through carefully crafted prompting.

In this work, we present our approach to addressing all subtasks of the BioLaySumm 2025 shared task by leveraging prompting and retrieval strategies, as well as multimodal input fusion. Our method integrates: (1) zero-shot and few-shot prompting with large language models (LLMs); (2) semantic similarity-based dynamic few-shot prompting; (3) retrieval-augmented generation (RAG) incorporating biomedical knowledge from the Unified Medical Language System (UMLS); and (4) a multimodal fusion pipeline that combines images and captions using image-text-to-text generation for enriched lay summarization. Our framework enables lightweight adaptation of pretrained LLMs for generating lay summaries from scientific articles and radiology reports. Using modern LLMs, including Llama-3.3-70B-Instruct and GPT-4.1, our 5cNLP team achieved third place in Subtask 1.2 and second place in Subtask 2.1, among all submissions.