Exploring instructive prompts for large language models in the extraction of evidence for supporting assigned suicidal risk levels

Monitoring and predicting the expression of suicidal risk in individuals’ social media posts is a central focus in clinical NLP. Yet, existing approaches frequently lack a crucial explainability component necessary for extracting evidence related to an individual’s mental health state. We describe the CSIRO Data61 team’s evidence extraction system submitted to the CLPsych 2024 shared task. The task aims to investigate the zero-shot capabilities of open-source LLM in extracting evidence regarding an individual’s assigned suicide risk level from social media discourse. The results are assessed against ground truth evidence annotated by psychological experts, with an achieved recall-oriented BERTScore of 0.919. Our findings suggest that LLMs showcase strong feasibility in the extraction of information supporting the evaluation of suicidal risk in social media discourse. Opportunities for refinement exist, notably in crafting concise and effective instructions to guide the extraction process.