We introduce a hybrid abstractive summarisation approach combining hierarchical VAE with LLMs (LlaMA-2) to produce clinically meaningful summaries from social media user timelines, appropriate for mental health monitoring. The summaries combine two different narrative points of view: clinical insights in third person useful for a clinician are generated by feeding into an LLM specialised clinical prompts, and importantly, a temporally sensitive abstractive summary of the user's timeline in first person, generated by a novel hierarchical variational autoencoder, TH-VAE. We assess the generated summaries via automatic evaluation against expert summaries and via human evaluation with clinical experts, showing that timeline summarisation by TH-VAE results in more factual and logically coherent summaries rich in clinical utility and superior to LLM-only approaches in capturing changes over time.
@article{arxiv.2401.16240,
title = {Combining Hierachical VAEs with LLMs for clinically meaningful timeline summarisation in social media},
author = {Jiayu Song and Jenny Chim and Adam Tsakalidis and Julia Ive and Dana Atzil-Slonim and Maria Liakata},
journal= {arXiv preprint arXiv:2401.16240},
year = {2024}
}