Combining Hierachical VAEs with LLMs for clinically meaningful timeline summarisation in social media

arXiv:2401.16240v2 Announce Type: replace
Abstract: 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 …

abstract arxiv clinical cs.ai cs.cl health hierarchical hybrid insights llama llms media mental health monitoring narrative person social social media timeline type vae view