Lune

ACL Findings2024

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

Jiayu Song, Jenny Chim, Adam Tsakalidis, Julia Ive, Dana Atzil-Slonim, Maria Liakata

Abstract

We introduce a hybrid abstractive summarisation approach combining hierarchical VAEs with LLMs to produce clinically meaningful summaries from social media user timelines, appropriate for mental health monitoring. The summaries combine two different narrative points of view: (a) clinical insights in third person, generated by feeding into an LLM clinical expert-guided prompts, and importantly, (b) 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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Language Models of Code Are Few-Shot Planners and Reasoners for Multi-Document Summarization with Attribution cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • Language Models of Code Are Few-Shot Planners and Reasoners for Multi-Document Summarization with Attribution cites BERTScore: Evaluating Text Generation with BERT
  • BARTScore: Evaluating Generated Text as Text Generation cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • BARTScore: Evaluating Generated Text as Text Generation cites BERTScore: Evaluating Text Generation with BERT
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Temporal reasoning for timeline summarisation in social mediaJiayu Song, Mahmud Elahi Akhter, Dana Atzil-Slonim, Maria LiakataACL 2025 · 6 citations
  2. Language Models of Code Are Few-Shot Planners and Reasoners for Multi-Document Summarization with AttributionAbhilash Nandy, Sambaran BandyopadhyayAAAI 2025 · 3 citations

Builds on14

  1. BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
  2. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  3. BARTScore: Evaluating Generated Text as Text GenerationWeizhe Yuan, Graham Neubig, Pengfei LiuNeurIPS 2021 · 1,143 citations
  4. NVAE: A Deep Hierarchical Variational AutoencoderArash Vahdat, Jan KautzNeurIPS 2020 · 1,141 citations
  5. Adversarial NLI: A New Benchmark for Natural Language UnderstandingYixin Nie, Adina Williams, Emily Dinan, Mohit Bansal et al.ACL 2020 · 602 citations

Related papers

  1. From Classification to Clinical Insights: Towards Analyzing and Reasoning About Mobile and Behavioral Health Data With Large Language ModelsZachary Englhardt, Chengqian Ma, Margaret E. Morris, Chun-Cheng Chang et al.UbiComp 2024 · 51 citations
  2. MIND: Empowering Mental Health Clinicians with Multimodal Data Insights through a Narrative DashboardRuishi Zou, Shiyu Xu, Margaret E. Morris, Jihan Ryu et al.CHI 2026 · 2 citations
  3. From Moments to Milestones: Incremental Timeline Summarization Leveraging Large Language ModelsQisheng Hu, Geonsik Moon, Hwee Tou NgACL 2024 · 8 citations
  4. MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' JournalingTaewan Kim, Seolyeong Bae, Hyun Ah Kim, Su-Woo Lee et al.CHI 2024 · 112 citations
  5. TimelineReasoner: Advancing Timeline Summarization with Large Reasoning ModelsLiancheng Zhang, Xiaoxi Li, Zhicheng DouSIGIR 2026
Dusk over the sea between two cliffs drawn in fine vertical lines