Lune

EMNLP Findings2025

SMARTMiner: Extracting and Evaluating SMART Goals from Low-Resource Health Coaching Notes

Iva Bojic, Qi Chwen Ong, Stephanie Hilary Xinyi Ma, Lin Ai, Zheng Liu, Ziwei Gong, Julia Hirschberg, Andy Hau Yan Ho, Andy W. H. Khong

Abstract

We present SMARTMiner, a framework for extracting and evaluating specific, measurable, attainable, relevant, time-bound (SMART) goals from unstructured health coaching (HC) notes. Developed in response to challenges observed during a clinical trial, the SMART-Miner achieves two tasks: (i) extracting behavior change goal spans and (ii) categorizing their SMARTness. We also introduce SMARTSpan, the first publicly available dataset of 173 HC notes annotated with 266 goals and SMART attributes. SMARTMiner incorporates an extractive goal retriever with a component-wise SMARTness classifier. Experiment results show that extractive models significantly outperformed their generative counterparts in low-resource settings, and that twostage fine-tuning substantially boosted performance. The SMARTness classifier achieved up to 0.91 SMART F1 score, while the full SMARTMiner maintained high end-to-end accuracy. This work bridges healthcare, behavioral science, and natural language processing to support health coaches and clients with structured goal tracking-paving way for automated weekly goal reviews between human-led HC sessions. Both the code and the dataset are available at: https://github. com/IvaBojic/SMARTMiner.

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.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • LoRA: Low-Rank Adaptation of Large Language Models cites Deberta: decoding-Enhanced Bert with Disentangled Attention
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on8

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu ChenICLR 2021 · 3,729 citations
  3. Question Answering with Long Multiple-Span AnswersMing Zhu, Aman Ahuja, Da-Cheng Juan, Wei Wei et al.EMNLP Findings 2020 · 63 citations
  4. LIQUID: A Framework for List Question Answering Dataset GenerationSeongyun Lee, Hyunjae Kim, Jaewoo KangAAAI 2023 · 31 citations
  5. A Survey on Open Information Extraction from Rule-based Model to Large Language ModelPai Liu, Wenyang Gao, Wenjie Dong, Lin Ai et al.EMNLP Findings 2024 · 13 citations

Related papers

  1. An LLM-Based Motivation-Aware Framework For AI Coaching For Behaviour ChangeVan Hoang, Eoin Rogers, Robert J. RossCHI 2026 · 2 citations
  2. Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical TextAvijit Mitra, Zhichao Yang, Emily Druhl, Raelene Goodwin et al.EMNLP 2025
  3. Bloom: Designing for LLM-Augmented Behavior Change InteractionsMatthew Jörke, Defne Genç, Valentin Teutschbein, Shardul Sapkota et al.CHI 2026 · 6 citations
  4. Benchmarking Large Language Models on Communicative Medical Coaching: A Dataset and a Novel SystemHengguan Huang, Songtao Wang, Hongfu Liu, Hao Wang et al.ACL Findings 2024 · 7 citations
  5. T2 Coach: A Qualitative Study of an Automated Health Coach for Diabetes Self-ManagementElliot G. Mitchell, Pooja M. Desai, Arlene M. Smaldone, Andrea Cassells et al.CHI 2025 · 10 citations
Dusk over the sea between two cliffs drawn in fine vertical lines