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.

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.